Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Matthew E. Taylor
@article{DBLP:journals/jair/RetzlaffDWMAYSATH24,
author = {Carl Orge Retzlaff and
Srijita Das and
Christabel Wayllace and
Payam Mousavi and
Mohammad Afshari and
Tianpei Yang and
Anna Saranti and
Alessa Angerschmid and
Matthew E. Taylor and
Andreas Holzinger},
title = {Human-in-the-Loop Reinforcement Learning: {A} Survey and Position
on Requirements, Challenges, and Opportunities},
journal = {J. Artif. Intell. Res.},
volume = {79},
pages = {359--415},
year = {2024},
url = {https://doi.org/10.1613/jair.1.15348},
doi = {10.1613/JAIR.1.15348},
timestamp = {Fri, 16 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jair/RetzlaffDWMAYSATH24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nca/PiersonAMT24,
author = {Brittany Davis Pierson and
Dustin Arendt and
John Miller and
Matthew E. Taylor},
title = {Comparing explanations in {RL}},
journal = {Neural Comput. Appl.},
volume = {36},
number = {1},
pages = {505--516},
year = {2024},
url = {https://doi.org/10.1007/s00521-023-08696-6},
doi = {10.1007/S00521-023-08696-6},
timestamp = {Fri, 26 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/nca/PiersonAMT24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/WuHYHZWT24,
author = {Jizhou Wu and
Jianye Hao and
Tianpei Yang and
Xiaotian Hao and
Yan Zheng and
Weixun Wang and
Matthew E. Taylor},
editor = {Michael J. Wooldridge and
Jennifer G. Dy and
Sriraam Natarajan},
title = {{PORTAL:} Automatic Curricula Generation for Multiagent Reinforcement
Learning},
booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}
2024, Thirty-Sixth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,
Canada},
pages = {15934--15942},
publisher = {{AAAI} Press},
year = {2024},
url = {https://doi.org/10.1609/aaai.v38i14.29524},
doi = {10.1609/AAAI.V38I14.29524},
timestamp = {Tue, 02 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/WuHYHZWT24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/YangYHZT24,
author = {Tianpei Yang and
Heng You and
Jianye Hao and
Yan Zheng and
Matthew E. Taylor},
editor = {Michael J. Wooldridge and
Jennifer G. Dy and
Sriraam Natarajan},
title = {A Transfer Approach Using Graph Neural Networks in Deep Reinforcement
Learning},
booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}
2024, Thirty-Sixth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,
Canada},
pages = {16352--16360},
publisher = {{AAAI} Press},
year = {2024},
url = {https://doi.org/10.1609/aaai.v38i15.29571},
doi = {10.1609/AAAI.V38I15.29571},
timestamp = {Tue, 02 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/YangYHZT24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-00907,
author = {Qianxi Li and
Yingyue Cao and
Jikun Kang and
Tianpei Yang and
Xi Chen and
Jun Jin and
Matthew E. Taylor},
title = {LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning
Language Models},
journal = {CoRR},
volume = {abs/2401.00907},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.00907},
doi = {10.48550/ARXIV.2401.00907},
eprinttype = {arXiv},
eprint = {2401.00907},
timestamp = {Mon, 15 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-00907.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-02991,
author = {Chaitanya Kharyal and
Sai Krishna Gottipati and
Tanmay Kumar Sinha and
Srijita Das and
Matthew E. Taylor},
title = {{GLIDE-RL:} Grounded Language Instruction through DEmonstration in
{RL}},
journal = {CoRR},
volume = {abs/2401.02991},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.02991},
doi = {10.48550/ARXIV.2401.02991},
eprinttype = {arXiv},
eprint = {2401.02991},
timestamp = {Tue, 23 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-02991.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-06819,
author = {Simone Parisi and
Montaser Mohammedalamen and
Alireza Kazemipour and
Matthew E. Taylor and
Michael Bowling},
title = {Monitored Markov Decision Processes},
journal = {CoRR},
volume = {abs/2402.06819},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.06819},
doi = {10.48550/ARXIV.2402.06819},
eprinttype = {arXiv},
eprint = {2402.06819},
timestamp = {Fri, 16 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-06819.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/YangWHTLHHCFRHZG23,
author = {Tianpei Yang and
Weixun Wang and
Jianye Hao and
Matthew E. Taylor and
Yong Liu and
Xiaotian Hao and
Yujing Hu and
Yingfeng Chen and
Changjie Fan and
Chunxu Ren and
Ye Huang and
Jiangcheng Zhu and
Yang Gao},
title = {{ASN:} action semantics network for multiagent reinforcement learning},
journal = {Auton. Agents Multi Agent Syst.},
volume = {37},
number = {2},
pages = {45},
year = {2023},
url = {https://doi.org/10.1007/s10458-023-09628-3},
doi = {10.1007/S10458-023-09628-3},
timestamp = {Thu, 07 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/aamas/YangWHTLHHCFRHZG23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jaihc/BignoldCTBDVF23,
author = {Adam Bignold and
Francisco Cruz and
Matthew E. Taylor and
Tim Brys and
Richard Dazeley and
Peter Vamplew and
Cameron Foale},
title = {A conceptual framework for externally-influenced agents: an assisted
reinforcement learning review},
journal = {J. Ambient Intell. Humaniz. Comput.},
volume = {14},
number = {4},
pages = {3621--3644},
year = {2023},
url = {https://doi.org/10.1007/s12652-021-03489-y},
doi = {10.1007/S12652-021-03489-Y},
timestamp = {Sun, 16 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jaihc/BignoldCTBDVF23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nca/TaylorNWN23,
author = {Matthew E. Taylor and
Nicholas Nissen and
Yuan Wang and
Neda Navidi},
title = {Improving reinforcement learning with human assistance: an argument
for human subject studies with {HIPPO} Gym},
journal = {Neural Comput. Appl.},
volume = {35},
number = {32},
pages = {23429--23439},
year = {2023},
url = {https://doi.org/10.1007/s00521-021-06375-y},
doi = {10.1007/S00521-021-06375-Y},
timestamp = {Fri, 27 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nca/TaylorNWN23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmlr/TomarMZT23,
author = {Manan Tomar and
Utkarsh A. Mishra and
Amy Zhang and
Matthew E. Taylor},
title = {Learning Representations for Pixel-based Control: What Matters and
Why?},
journal = {Trans. Mach. Learn. Res.},
volume = {2023},
year = {2023},
url = {https://openreview.net/forum?id=wIXHG8LZ2w},
timestamp = {Thu, 18 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tmlr/TomarMZT23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/MguniJWNSTTYDCZ23,
author = {David Mguni and
Taher Jafferjee and
Jianhong Wang and
Nicolas Perez Nieves and
Wenbin Song and
Feifei Tong and
Matthew E. Taylor and
Tianpei Yang and
Zipeng Dai and
Hui Chen and
Jiangcheng Zhu and
Kun Shao and
Jun Wang and
Yaodong Yang},
editor = {Brian Williams and
Yiling Chen and
Jennifer Neville},
title = {Learning to Shape Rewards Using a Game of Two Partners},
booktitle = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence, {AAAI}
2023, Thirty-Fifth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2023, Thirteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2023, Washington, DC, USA, February
7-14, 2023},
pages = {11604--11612},
publisher = {{AAAI} Press},
year = {2023},
url = {https://doi.org/10.1609/aaai.v37i10.26371},
doi = {10.1609/AAAI.V37I10.26371},
timestamp = {Thu, 02 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaai/MguniJWNSTTYDCZ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/NellerWDYBTDTPT23,
author = {Todd W. Neller and
Raechel Walker and
Olivia Dias and
Zeynep Yal{\c{c}}in and
Cynthia Breazeal and
Matthew E. Taylor and
Michele Donini and
Erin J. Talvitie and
Charlie Pilgrim and
Paolo Turrini and
James Maher and
Matthew Boutell and
Justin Wilson and
Narges Norouzi and
Jonathan Scott},
editor = {Brian Williams and
Yiling Chen and
Jennifer Neville},
title = {Model {AI} Assignments 2023},
booktitle = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence, {AAAI}
2023, Thirty-Fifth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2023, Thirteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2023, Washington, DC, USA, February
7-14, 2023},
pages = {16104--16105},
publisher = {{AAAI} Press},
year = {2023},
url = {https://doi.org/10.1609/aaai.v37i13.26913},
doi = {10.1609/AAAI.V37I13.26913},
timestamp = {Wed, 13 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/NellerWDYBTDTPT23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/GuevarraDWETT23,
author = {Michael Guevarra and
Srijita Das and
Christabel Wayllace and
Carrie Demmans Epp and
Matthew E. Taylor and
Alan Tay},
editor = {Brian Williams and
Yiling Chen and
Jennifer Neville},
title = {Augmenting Flight Training with {AI} to Efficiently Train Pilots},
booktitle = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence, {AAAI}
2023, Thirty-Fifth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2023, Thirteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2023, Washington, DC, USA, February
7-14, 2023},
pages = {16437--16439},
publisher = {{AAAI} Press},
year = {2023},
url = {https://doi.org/10.1609/aaai.v37i13.27071},
doi = {10.1609/AAAI.V37I13.27071},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/GuevarraDWETT23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aied/MuslimaniGTEW23,
author = {Calarina Muslimani and
Saba Gul and
Matthew E. Taylor and
Carrie Demmans Epp and
Christabel Wayllace},
editor = {Ning Wang and
Genaro Rebolledo{-}Mendez and
Noboru Matsuda and
Olga C. Santos and
Vania Dimitrova},
title = {C\({}^{\mbox{2}}\)Tutor: Helping People Learn to Avoid Present Bias
During Decision Making},
booktitle = {Artificial Intelligence in Education - 24th International Conference,
{AIED} 2023, Tokyo, Japan, July 3-7, 2023, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {13916},
pages = {733--738},
publisher = {Springer},
year = {2023},
url = {https://doi.org/10.1007/978-3-031-36272-9\_64},
doi = {10.1007/978-3-031-36272-9\_64},
timestamp = {Fri, 04 Aug 2023 15:27:47 +0200},
biburl = {https://dblp.org/rec/conf/aied/MuslimaniGTEW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SubramanianTL023,
author = {Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Kate Larson and
Mark Crowley},
editor = {Noa Agmon and
Bo An and
Alessandro Ricci and
William Yeoh},
title = {Learning from Multiple Independent Advisors in Multi-agent Reinforcement
Learning},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2023, London, United Kingdom, 29 May
2023 - 2 June 2023},
pages = {1144--1153},
publisher = {{ACM}},
year = {2023},
url = {https://dl.acm.org/doi/10.5555/3545946.3598756},
doi = {10.5555/3545946.3598756},
timestamp = {Tue, 23 May 2023 14:27:14 +0200},
biburl = {https://dblp.org/rec/conf/atal/SubramanianTL023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/GrootenSDMTPM23,
author = {Bram Grooten and
Ghada Sokar and
Shibhansh Dohare and
Elena Mocanu and
Matthew E. Taylor and
Mykola Pechenizkiy and
Decebal Constantin Mocanu},
editor = {Noa Agmon and
Bo An and
Alessandro Ricci and
William Yeoh},
title = {Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement
Learning},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2023, London, United Kingdom, 29 May
2023 - 2 June 2023},
pages = {1932--1941},
publisher = {{ACM}},
year = {2023},
url = {https://dl.acm.org/doi/10.5555/3545946.3598862},
doi = {10.5555/3545946.3598862},
timestamp = {Tue, 23 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/GrootenSDMTPM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/KharyalSGADT23,
author = {Chaitanya Kharyal and
Tanmay Kumar Sinha and
Sai Krishna Gottipati and
Fatemeh Abdollahi and
Srijita Das and
Matthew E. Taylor},
editor = {Noa Agmon and
Bo An and
Alessandro Ricci and
William Yeoh},
title = {Do As You Teach: {A} Multi-Teacher Approach to Self-Play in Deep Reinforcement
Learning},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2023, London, United Kingdom, 29 May
2023 - 2 June 2023},
pages = {2457--2459},
publisher = {{ACM}},
year = {2023},
url = {https://dl.acm.org/doi/10.5555/3545946.3598966},
doi = {10.5555/3545946.3598966},
timestamp = {Tue, 23 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/KharyalSGADT23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/WuYHHZWT23,
author = {Jizhou Wu and
Tianpei Yang and
Xiaotian Hao and
Jianye Hao and
Yan Zheng and
Weixun Wang and
Matthew E. Taylor},
editor = {Noa Agmon and
Bo An and
Alessandro Ricci and
William Yeoh},
title = {{PORTAL:} Automatic Curricula Generation for Multiagent Reinforcement
Learning},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2023, London, United Kingdom, 29 May
2023 - 2 June 2023},
pages = {2460--2462},
publisher = {{ACM}},
year = {2023},
url = {https://dl.acm.org/doi/10.5555/3545946.3598967},
doi = {10.5555/3545946.3598967},
timestamp = {Tue, 23 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/WuYHHZWT23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ZhangDST23,
author = {Su Zhang and
Srijita Das and
Sriram Ganapathi Subramanian and
Matthew E. Taylor},
editor = {Noa Agmon and
Bo An and
Alessandro Ricci and
William Yeoh},
title = {Two-Level Actor-Critic Using Multiple Teachers},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2023, London, United Kingdom, 29 May
2023 - 2 June 2023},
pages = {2589--2591},
publisher = {{ACM}},
year = {2023},
url = {https://dl.acm.org/doi/10.5555/3545946.3599011},
doi = {10.5555/3545946.3599011},
timestamp = {Tue, 23 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/ZhangDST23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/CairoEMSJTDKMMM23,
author = {Mara Cairo and
Bevin Eldaphonse and
Payam Mousavi and
Sahir and
Sheikh Jubair and
Matthew E. Taylor and
Graham Doerksen and
Nikolai Kummer and
Jordan Maretzki and
Gupreet Mohhar and
Sean Murphy and
Johannes G{\"{u}}nther and
Laura Petrich and
Talat Syed},
editor = {Noa Agmon and
Bo An and
Alessandro Ricci and
William Yeoh},
title = {Multi-Robot Warehouse Optimization: Leveraging Machine Learning for
Improved Performance},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2023, London, United Kingdom, 29 May
2023 - 2 June 2023},
pages = {3047--3049},
publisher = {{ACM}},
year = {2023},
url = {https://dl.acm.org/doi/10.5555/3545946.3599168},
doi = {10.5555/3545946.3599168},
timestamp = {Wed, 30 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/CairoEMSJTDKMMM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/GottipatiNMT23,
author = {Sai Krishna Gottipati and
Luong{-}Ha Nguyen and
Clod{\'{e}}ric Mars and
Matthew E. Taylor},
editor = {Noa Agmon and
Bo An and
Alessandro Ricci and
William Yeoh},
title = {Hiking up that {HILL} with Cogment-Verse: Train {\&} Operate Multi-agent
Systems Learning from Humans},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2023, London, United Kingdom, 29 May
2023 - 2 June 2023},
pages = {3065--3067},
publisher = {{ACM}},
year = {2023},
url = {https://dl.acm.org/doi/10.5555/3545946.3599174},
doi = {10.5555/3545946.3599174},
timestamp = {Tue, 23 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/GottipatiNMT23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fie/DuATDB23,
author = {Xiaoxue Du and
Sharifa Alghowinem and
Matthew E. Taylor and
Kate Darling and
Cynthia Breazeal},
title = {Innovating {AI} Leadership Education},
booktitle = {{IEEE} Frontiers in Education Conference, {FIE} 2023, College Station,
TX, USA, October 18-21, 2023},
pages = {1--8},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/FIE58773.2023.10343238},
doi = {10.1109/FIE58773.2023.10343238},
timestamp = {Thu, 25 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/fie/DuATDB23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/glvlsi/GandhiABMTB23,
author = {Upma Gandhi and
Erfan Aghaeekiasaraee and
Ismail S. K. Bustany and
Payam Mousavi and
Matthew E. Taylor and
Laleh Behjat},
editor = {Himanshu Thapliyal and
Ronald F. DeMara and
Inna Partin{-}Vaisband and
Srinivas Katkoori},
title = {RL-Ripper: : {A} Framework for Global Routing Using Reinforcement
Learning and Smart Net Ripping Techniques},
booktitle = {Proceedings of the Great Lakes Symposium on {VLSI} 2023, {GLSVLSI}
2023, Knoxville, TN, USA, June 5-7, 2023},
pages = {197--201},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3583781.3590312},
doi = {10.1145/3583781.3590312},
timestamp = {Thu, 15 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/glvlsi/GandhiABMTB23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hhai/Taylor23,
author = {Matthew E. Taylor},
editor = {Paul Lukowicz and
Sven Mayer and
Janin Koch and
John Shawe{-}Taylor and
Ilaria Tiddi},
title = {Reinforcement Learning Requires Human-in-the-Loop Framing and Approaches},
booktitle = {{HHAI} 2023: Augmenting Human Intellect - Proceedings of the Second
International Conference on Hybrid Human-Artificial Intelligence,
June 26-30, 2023, Munich, Germany},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {368},
pages = {351--360},
publisher = {{IOS} Press},
year = {2023},
url = {https://doi.org/10.3233/FAIA230098},
doi = {10.3233/FAIA230098},
timestamp = {Wed, 28 Jun 2023 11:34:08 +0200},
biburl = {https://dblp.org/rec/conf/hhai/Taylor23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/AbdollahiATL23,
author = {Fatemeh Abdollahi and
Saqib Ameen and
Matthew E. Taylor and
Levi H. S. Lelis},
title = {Can You Improve My Code? Optimizing Programs with Local Search},
booktitle = {Proceedings of the Thirty-Second International Joint Conference on
Artificial Intelligence, {IJCAI} 2023, 19th-25th August 2023, Macao,
SAR, China},
pages = {2940--2948},
publisher = {ijcai.org},
year = {2023},
url = {https://doi.org/10.24963/ijcai.2023/328},
doi = {10.24963/IJCAI.2023/328},
timestamp = {Mon, 28 Aug 2023 17:23:07 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/AbdollahiATL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/SubramanianTL023,
author = {Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Kate Larson and
Mark Crowley},
title = {Multi-Agent Advisor Q-Learning (Extended Abstract)},
booktitle = {Proceedings of the Thirty-Second International Joint Conference on
Artificial Intelligence, {IJCAI} 2023, 19th-25th August 2023, Macao,
SAR, China},
pages = {6884--6889},
publisher = {ijcai.org},
year = {2023},
url = {https://doi.org/10.24963/ijcai.2023/776},
doi = {10.24963/IJCAI.2023/776},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/SubramanianTL023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/TomarITLB23,
author = {Manan Tomar and
Riashat Islam and
Matthew E. Taylor and
Sergey Levine and
Philip Bachman},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Ignorance is Bliss: Robust Control via Information Gating},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/797be96e4481c3fe5d675c1ba5352969-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/TomarITLB23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-11153,
author = {Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Kate Larson and
Mark Crowley},
title = {Learning from Multiple Independent Advisors in Multi-agent Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2301.11153},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.11153},
doi = {10.48550/ARXIV.2301.11153},
eprinttype = {arXiv},
eprint = {2301.11153},
timestamp = {Tue, 31 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-11153.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-06548,
author = {Bram Grooten and
Ghada Sokar and
Shibhansh Dohare and
Elena Mocanu and
Matthew E. Taylor and
Mykola Pechenizkiy and
Decebal Constantin Mocanu},
title = {Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2302.06548},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.06548},
doi = {10.48550/ARXIV.2302.06548},
eprinttype = {arXiv},
eprint = {2302.06548},
timestamp = {Mon, 20 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-06548.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-05603,
author = {Fatemeh Abdollahi and
Saqib Ameen and
Matthew E. Taylor and
Levi H. S. Lelis},
title = {Can You Improve My Code? Optimizing Programs with Local Search},
journal = {CoRR},
volume = {abs/2307.05603},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.05603},
doi = {10.48550/ARXIV.2307.05603},
eprinttype = {arXiv},
eprint = {2307.05603},
timestamp = {Mon, 24 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-05603.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-00810,
author = {Afia Abedin and
Abdul Bais and
Cody Buntain and
Laura Courchesne and
Brian McQuinn and
Matthew E. Taylor and
Muhib Ullah},
title = {A Call to Arms: {AI} Should be Critical for Social Media Analysis
of Conflict Zones},
journal = {CoRR},
volume = {abs/2311.00810},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.00810},
doi = {10.48550/ARXIV.2311.00810},
eprinttype = {arXiv},
eprint = {2311.00810},
timestamp = {Tue, 07 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-00810.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-11718,
author = {Laila El Moujtahid and
Sai Krishna Gottipati and
Clod{\'{e}}ric Mars and
Matthew E. Taylor},
title = {Human-Machine Teaming for UAVs: An Experimentation Platform},
journal = {CoRR},
volume = {abs/2312.11718},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.11718},
doi = {10.48550/ARXIV.2312.11718},
eprinttype = {arXiv},
eprint = {2312.11718},
timestamp = {Tue, 16 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-11718.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-11768,
author = {Rupali Bhati and
Sai Krishna Gottipati and
Clod{\'{e}}ric Mars and
Matthew E. Taylor},
title = {Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning},
journal = {CoRR},
volume = {abs/2312.11768},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.11768},
doi = {10.48550/ARXIV.2312.11768},
eprinttype = {arXiv},
eprint = {2312.11768},
timestamp = {Tue, 16 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-11768.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-15160,
author = {Md Saiful Islam and
Srijita Das and
Sai Krishna Gottipati and
William Duguay and
Clod{\'{e}}ric Mars and
Jalal Arabneydi and
Antoine Fagette and
Matthew Guzdial and
Matthew E. Taylor},
title = {Human-AI Collaboration in Real-World Complex Environment with Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2312.15160},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.15160},
doi = {10.48550/ARXIV.2312.15160},
eprinttype = {arXiv},
eprint = {2312.15160},
timestamp = {Thu, 18 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-15160.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-15339,
author = {Bram Grooten and
Tristan Tomilin and
Gautham Vasan and
Matthew E. Taylor and
A. Rupam Mahmood and
Meng Fang and
Mykola Pechenizkiy and
Decebal Constantin Mocanu},
title = {MaDi: Learning to Mask Distractions for Generalization in Visual Deep
Reinforcement Learning},
journal = {CoRR},
volume = {abs/2312.15339},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.15339},
doi = {10.48550/ARXIV.2312.15339},
eprinttype = {arXiv},
eprint = {2312.15339},
timestamp = {Thu, 18 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-15339.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/SubramanianTLC22,
author = {Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Kate Larson and
Mark Crowley},
title = {Multi-Agent Advisor Q-Learning},
journal = {J. Artif. Intell. Res.},
volume = {74},
pages = {1--74},
year = {2022},
url = {https://doi.org/10.1613/jair.1.13445},
doi = {10.1613/JAIR.1.13445},
timestamp = {Thu, 12 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jair/SubramanianTLC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nca/BehboudianSTHB22,
author = {Paniz Behboudian and
Yash Satsangi and
Matthew E. Taylor and
Anna Harutyunyan and
Michael Bowling},
title = {Policy invariant explicit shaping: an efficient alternative to reward
shaping},
journal = {Neural Comput. Appl.},
volume = {34},
number = {3},
pages = {1673--1686},
year = {2022},
url = {https://doi.org/10.1007/s00521-021-06259-1},
doi = {10.1007/S00521-021-06259-1},
timestamp = {Fri, 13 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nca/BehboudianSTHB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nca/DuWGST22,
author = {Yunshu Du and
Garrett Warnell and
Assefaw H. Gebremedhin and
Peter Stone and
Matthew E. Taylor},
title = {Lucid dreaming for experience replay: refreshing past states with
the current policy},
journal = {Neural Comput. Appl.},
volume = {34},
number = {3},
pages = {1687--1712},
year = {2022},
url = {https://doi.org/10.1007/s00521-021-06104-5},
doi = {10.1007/S00521-021-06104-5},
timestamp = {Wed, 23 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/nca/DuWGST22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SubramanianT0P22,
author = {Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Mark Crowley and
Pascal Poupart},
title = {Decentralized Mean Field Games},
booktitle = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
- March 1, 2022},
pages = {9439--9447},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i9.21176},
doi = {10.1609/AAAI.V36I9.21176},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SubramanianT0P22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eenergy/ZhangSAMTA22,
author = {Tianyu Zhang and
Aakash Krishna G. S and
Mohammad Afshari and
Petr Mus{\'{\i}}lek and
Matthew E. Taylor and
Omid Ardakanian},
editor = {Sebastian Lehnhoff and
David E. Irwin and
Dan Wang},
title = {Diversity for transfer in learning-based control of buildings},
booktitle = {e-Energy '22: The Thirteenth {ACM} International Conference on Future
Energy Systems, Virtual Event, 28 June 2022 - 1 July 2022},
pages = {556--564},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3538637.3539615},
doi = {10.1145/3538637.3539615},
timestamp = {Wed, 27 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eenergy/ZhangSAMTA22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LiTYHSZHTTW22,
author = {Pengyi Li and
Hongyao Tang and
Tianpei Yang and
Xiaotian Hao and
Tong Sang and
Yan Zheng and
Jianye Hao and
Matthew E. Taylor and
Wenyuan Tao and
Zhen Wang},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {{PMIC:} Improving Multi-Agent Reinforcement Learning with Progressive
Mutual Information Collaboration},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {12979--12997},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/li22s.html},
timestamp = {Tue, 12 Jul 2022 17:36:52 +0200},
biburl = {https://dblp.org/rec/conf/icml/LiTYHSZHTTW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HuangLSZT0WMH0D22,
author = {Wenhan Huang and
Kai Li and
Kun Shao and
Tianze Zhou and
Matthew E. Taylor and
Jun Luo and
Dongge Wang and
Hangyu Mao and
Jianye Hao and
Jun Wang and
Xiaotie Deng},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Multiagent Q-learning with Sub-Team Coordination},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/bd31bfd4caa85bffe07a35568182cdfa-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/HuangLSZT0WMH0D22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/YouYZHT22,
author = {Heng You and
Tianpei Yang and
Yan Zheng and
Jianye Hao and
Matthew E. Taylor},
editor = {James Cussens and
Kun Zhang},
title = {Cross-domain adaptive transfer reinforcement learning based on state-action
correspondence},
booktitle = {Uncertainty in Artificial Intelligence, Proceedings of the Thirty-Eighth
Conference on Uncertainty in Artificial Intelligence, {UAI} 2022,
1-5 August 2022, Eindhoven, The Netherlands},
series = {Proceedings of Machine Learning Research},
volume = {180},
pages = {2299--2309},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v180/you22a.html},
timestamp = {Sat, 15 Oct 2022 12:08:13 +0200},
biburl = {https://dblp.org/rec/conf/uai/YouYZHT22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/atal/2022,
editor = {Piotr Faliszewski and
Viviana Mascardi and
Catherine Pelachaud and
Matthew E. Taylor},
title = {21st International Conference on Autonomous Agents and Multiagent
Systems, {AAMAS} 2022, Auckland, New Zealand, May 9-13, 2022},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems
{(IFAAMAS)}},
year = {2022},
url = {https://www.ifaamas.org/Proceedings/aamas2022},
doi = {10.5555/3535850},
isbn = {978-1-4503-9213-6},
timestamp = {Mon, 18 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/2022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-08553,
author = {Pengyi Li and
Hongyao Tang and
Tianpei Yang and
Xiaotian Hao and
Tong Sang and
Yan Zheng and
Jianye Hao and
Matthew E. Taylor and
Zhen Wang},
title = {{PMIC:} Improving Multi-Agent Reinforcement Learning with Progressive
Mutual Information Collaboration},
journal = {CoRR},
volume = {abs/2203.08553},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.08553},
doi = {10.48550/ARXIV.2203.08553},
eprinttype = {arXiv},
eprint = {2203.08553},
timestamp = {Mon, 28 Mar 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-08553.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-07254,
author = {Sahir and
Erc{\"{u}}ment Ilhan and
Srijita Das and
Matthew E. Taylor},
title = {Methodical Advice Collection and Reuse in Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/2204.07254},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.07254},
doi = {10.48550/ARXIV.2204.07254},
eprinttype = {arXiv},
eprint = {2204.07254},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-07254.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-11897,
author = {Alex Lewandowski and
Calarina Muslimani and
Matthew E. Taylor and
Jun Luo and
Dale Schuurmans},
title = {Reinforcement Teaching},
journal = {CoRR},
volume = {abs/2204.11897},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.11897},
doi = {10.48550/ARXIV.2204.11897},
eprinttype = {arXiv},
eprint = {2204.11897},
timestamp = {Thu, 28 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-11897.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-01054,
author = {Taher Jafferjee and
Juliusz Krysztof Ziomek and
Tianpei Yang and
Zipeng Dai and
Jianhong Wang and
Matthew E. Taylor and
Kun Shao and
Jun Wang and
David Mguni},
title = {Semi-Centralised Multi-Agent Reinforcement Learning with Policy-Embedded
Training},
journal = {CoRR},
volume = {abs/2209.01054},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.01054},
doi = {10.48550/ARXIV.2209.01054},
eprinttype = {arXiv},
eprint = {2209.01054},
timestamp = {Mon, 26 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-01054.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-06683,
author = {Michael Guevarra and
Srijita Das and
Christabel Wayllace and
Carrie Demmans Epp and
Matthew E. Taylor and
Alan Tay},
title = {Augmenting Flight Training with {AI} to Efficiently Train Pilots},
journal = {CoRR},
volume = {abs/2210.06683},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.06683},
doi = {10.48550/ARXIV.2210.06683},
eprinttype = {arXiv},
eprint = {2210.06683},
timestamp = {Tue, 18 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-06683.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-07545,
author = {Amir Rasouli and
Randy Goebel and
Matthew E. Taylor and
Iuliia Kotseruba and
Soheil Alizadeh and
Tianpei Yang and
Montgomery Alban and
Florian Shkurti and
Yuzheng Zhuang and
Adam {\'{S}}cibior and
Kasra Rezaee and
Animesh Garg and
David Meger and
Jun Luo and
Liam Paull and
Weinan Zhang and
Xinyu Wang and
Xi Chen},
title = {NeurIPS 2022 Competition: Driving {SMARTS}},
journal = {CoRR},
volume = {abs/2211.07545},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.07545},
doi = {10.48550/ARXIV.2211.07545},
eprinttype = {arXiv},
eprint = {2211.07545},
timestamp = {Wed, 16 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-07545.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-08302,
author = {Hager Radi and
Josiah P. Hanna and
Peter Stone and
Matthew E. Taylor},
title = {Safe Evaluation For Offline Learning: Are We Ready To Deploy?},
journal = {CoRR},
volume = {abs/2212.08302},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.08302},
doi = {10.48550/ARXIV.2212.08302},
eprinttype = {arXiv},
eprint = {2212.08302},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-08302.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/GottipatiPSSNAT21,
author = {Sai Krishna Gottipati and
Yashaswi Pathak and
Boris Sattarov and
Sahir and
Rohan Nuttall and
Mohammad Amini and
Matthew E. Taylor and
Sarath Chandar},
title = {Towered Actor Critic For Handling Multiple Action Types In Reinforcement
Learning For Drug Discovery},
booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI}
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9,
2021},
pages = {142--150},
publisher = {{AAAI} Press},
year = {2021},
url = {https://doi.org/10.1609/aaai.v35i1.16087},
doi = {10.1609/AAAI.V35I1.16087},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/GottipatiPSSNAT21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/YangLWSGBWT21,
author = {Yaodong Yang and
Jun Luo and
Ying Wen and
Oliver Slumbers and
Daniel Graves and
Haitham Bou{-}Ammar and
Jun Wang and
Matthew E. Taylor},
editor = {Frank Dignum and
Alessio Lomuscio and
Ulle Endriss and
Ann Now{\'{e}}},
title = {Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent
Learning Systems},
booktitle = {{AAMAS} '21: 20th International Conference on Autonomous Agents and
Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021},
pages = {51--56},
publisher = {{ACM}},
year = {2021},
url = {https://www.ifaamas.org/Proceedings/aamas2021/pdfs/p51.pdf},
doi = {10.5555/3463952.3463963},
timestamp = {Fri, 19 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/YangLWSGBWT21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SubramanianT0P21,
author = {Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Mark Crowley and
Pascal Poupart},
editor = {Frank Dignum and
Alessio Lomuscio and
Ulle Endriss and
Ann Now{\'{e}}},
title = {Partially Observable Mean Field Reinforcement Learning},
booktitle = {{AAMAS} '21: 20th International Conference on Autonomous Agents and
Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021},
pages = {537--545},
publisher = {{ACM}},
year = {2021},
url = {https://www.ifaamas.org/Proceedings/aamas2021/pdfs/p537.pdf},
doi = {10.5555/3463952.3464019},
timestamp = {Wed, 20 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/SubramanianT0P21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ispd/Taylor21,
author = {Matthew E. Taylor},
editor = {Jens Lienig and
Laleh Behjat and
Stephen Yang},
title = {Reinforcement Learning for Electronic Design Automation: Successes
and Opportunities},
booktitle = {{ISPD} '21: International Symposium on Physical Design, Virtual Event,
USA, March 22-24, 2021},
pages = {3},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3439706.3446882},
doi = {10.1145/3439706.3446882},
timestamp = {Mon, 12 Apr 2021 09:09:55 +0200},
biburl = {https://dblp.org/rec/conf/ispd/Taylor21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/RasouliAKMLTHLWGYTPC21,
author = {Amir Rasouli and
Soheil Alizadeh and
Iuliia Kotseruba and
Yi Ma and
Hebin Liang and
Yuan Tian and
Zhiyu Huang and
Haochen Liu and
Jingda Wu and
Randy Goebel and
Tianpei Yang and
Matthew E. Taylor and
Liam Paull and
Xi Chen},
editor = {Marco Ciccone and
Gustavo Stolovitzky and
Jacob Albrecht},
title = {Driving {SMARTS} Competition at NeurIPS 2022: Insights and Outcome},
booktitle = {NeurIPS 2022 Competition Track, November 28 - December 9, 2022, Online},
series = {Proceedings of Machine Learning Research},
volume = {220},
pages = {73--84},
publisher = {{PMLR}},
year = {2021},
url = {https://proceedings.mlr.press/v220/rasouli22a.html},
timestamp = {Mon, 04 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/RasouliAKMLTHLWGYTPC21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-00824,
author = {Nikunj Gupta and
G. Srinivasaraghavan and
Swarup Kumar Mohalik and
Matthew E. Taylor},
title = {{HAMMER:} Multi-Level Coordination of Reinforcement Learning Agents
via Learned Messaging},
journal = {CoRR},
volume = {abs/2102.00824},
year = {2021},
url = {https://arxiv.org/abs/2102.00824},
eprinttype = {arXiv},
eprint = {2102.00824},
timestamp = {Fri, 06 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-00824.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-02639,
author = {Matthew E. Taylor and
Nicholas Nissen and
Yuan Wang and
Neda Navidi},
title = {Improving Reinforcement Learning with Human Assistance: An Argument
for Human Subject Studies with {HIPPO} Gym},
journal = {CoRR},
volume = {abs/2102.02639},
year = {2021},
url = {https://arxiv.org/abs/2102.02639},
eprinttype = {arXiv},
eprint = {2102.02639},
timestamp = {Tue, 09 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-02639.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-07659,
author = {Yaodong Yang and
Jun Luo and
Ying Wen and
Oliver Slumbers and
Daniel Graves and
Haitham Bou{-}Ammar and
Jun Wang and
Matthew E. Taylor},
title = {Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent
Learning Systems},
journal = {CoRR},
volume = {abs/2102.07659},
year = {2021},
url = {https://arxiv.org/abs/2102.07659},
eprinttype = {arXiv},
eprint = {2102.07659},
timestamp = {Fri, 19 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-07659.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-09850,
author = {Manan Tomar and
Amy Zhang and
Roberto Calandra and
Matthew E. Taylor and
Joelle Pineau},
title = {Model-Invariant State Abstractions for Model-Based Reinforcement Learning},
journal = {CoRR},
volume = {abs/2102.09850},
year = {2021},
url = {https://arxiv.org/abs/2102.09850},
eprinttype = {arXiv},
eprint = {2102.09850},
timestamp = {Wed, 24 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-09850.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-04416,
author = {Volodymyr Tkachuk and
Sriram Ganapathi Subramanian and
Matthew E. Taylor},
title = {The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free,
Reinforcement Learning},
journal = {CoRR},
volume = {abs/2103.04416},
year = {2021},
url = {https://arxiv.org/abs/2103.04416},
eprinttype = {arXiv},
eprint = {2103.04416},
timestamp = {Mon, 15 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-04416.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-04893,
author = {Brittany Davis Pierson and
Justine Ventura and
Matthew E. Taylor},
title = {The Atari Data Scraper},
journal = {CoRR},
volume = {abs/2104.04893},
year = {2021},
url = {https://arxiv.org/abs/2104.04893},
eprinttype = {arXiv},
eprint = {2104.04893},
timestamp = {Mon, 19 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-04893.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-00345,
author = {Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Kate Larson and
Mark Crowley},
title = {Multi-Agent Advisor Q-Learning},
journal = {CoRR},
volume = {abs/2111.00345},
year = {2021},
url = {https://arxiv.org/abs/2111.00345},
eprinttype = {arXiv},
eprint = {2111.00345},
timestamp = {Fri, 05 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-00345.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-07775,
author = {Manan Tomar and
Utkarsh A. Mishra and
Amy Zhang and
Matthew E. Taylor},
title = {Learning Representations for Pixel-based Control: What Matters and
Why?},
journal = {CoRR},
volume = {abs/2111.07775},
year = {2021},
url = {https://arxiv.org/abs/2111.07775},
eprinttype = {arXiv},
eprint = {2111.07775},
timestamp = {Tue, 16 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-07775.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-09099,
author = {Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Mark Crowley and
Pascal Poupart},
title = {Decentralized Mean Field Games},
journal = {CoRR},
volume = {abs/2112.09099},
year = {2021},
url = {https://arxiv.org/abs/2112.09099},
eprinttype = {arXiv},
eprint = {2112.09099},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-09099.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/access/GhazanfariAT20,
author = {Behzad Ghazanfari and
Fatemeh Afghah and
Matthew E. Taylor},
title = {Sequential Association Rule Mining for Autonomously Extracting Hierarchical
Task Structures in Reinforcement Learning},
journal = {{IEEE} Access},
volume = {8},
pages = {11782--11799},
year = {2020},
url = {https://doi.org/10.1109/ACCESS.2020.2965930},
doi = {10.1109/ACCESS.2020.2965930},
timestamp = {Fri, 07 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/access/GhazanfariAT20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ce/HuWAT20,
author = {Yang Hu and
Rachel Min Wong and
Olusola O. Adesope and
Matthew E. Taylor},
title = {Effects of a computer-based learning environment that teaches older
adults how to install a smart home system},
journal = {Comput. Educ.},
volume = {149},
pages = {103816},
year = {2020},
url = {https://doi.org/10.1016/j.compedu.2020.103816},
doi = {10.1016/J.COMPEDU.2020.103816},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ce/HuWAT20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/NarvekarPLSTS20,
author = {Sanmit Narvekar and
Bei Peng and
Matteo Leonetti and
Jivko Sinapov and
Matthew E. Taylor and
Peter Stone},
title = {Curriculum Learning for Reinforcement Learning Domains: {A} Framework
and Survey},
journal = {J. Mach. Learn. Res.},
volume = {21},
pages = {181:1--181:50},
year = {2020},
url = {http://jmlr.org/papers/v21/20-212.html},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jmlr/NarvekarPLSTS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sensors/HuCT20,
author = {Yang Hu and
Diane J. Cook and
Matthew E. Taylor},
title = {Study of Effectiveness of Prior Knowledge for Smart Home Kit Installation},
journal = {Sensors},
volume = {20},
number = {21},
pages = {6145},
year = {2020},
url = {https://doi.org/10.3390/s20216145},
doi = {10.3390/S20216145},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/sensors/HuCT20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SilvaHKT20a,
author = {Felipe Leno da Silva and
Pablo Hernandez{-}Leal and
Bilal Kartal and
Matthew E. Taylor},
title = {Uncertainty-Aware Action Advising for Deep Reinforcement Learning
Agents},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {5792--5799},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i04.6036},
doi = {10.1609/AAAI.V34I04.6036},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SilvaHKT20a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SilvaHKT20,
author = {Felipe Leno da Silva and
Pablo Hernandez{-}Leal and
Bilal Kartal and
Matthew E. Taylor},
title = {Providing Uncertainty-Based Advice for Deep Reinforcement Learning
Agents (Student Abstract)},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {13913--13914},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i10.7229},
doi = {10.1609/AAAI.V34I10.7229},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SilvaHKT20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SubramanianPTH20,
author = {Sriram Ganapathi Subramanian and
Pascal Poupart and
Matthew E. Taylor and
Nidhi Hegde},
editor = {Amal El Fallah Seghrouchni and
Gita Sukthankar and
Bo An and
Neil Yorke{-}Smith},
title = {Multi Type Mean Field Reinforcement Learning},
booktitle = {Proceedings of the 19th International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} '20, Auckland, New Zealand, May 9-13,
2020},
pages = {411--419},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
year = {2020},
url = {https://dl.acm.org/doi/10.5555/3398761.3398813},
doi = {10.5555/3398761.3398813},
timestamp = {Tue, 26 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/SubramanianPTH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/Hernandez-LealK20,
author = {Pablo Hernandez{-}Leal and
Bilal Kartal and
Matthew E. Taylor},
editor = {Amal El Fallah Seghrouchni and
Gita Sukthankar and
Bo An and
Neil Yorke{-}Smith},
title = {A Very Condensed Survey and Critique of Multiagent Deep Reinforcement
Learning},
booktitle = {Proceedings of the 19th International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} '20, Auckland, New Zealand, May 9-13,
2020},
pages = {2146--2148},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
year = {2020},
url = {https://dl.acm.org/doi/10.5555/3398761.3399105},
doi = {10.5555/3398761.3399105},
timestamp = {Tue, 26 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/Hernandez-LealK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/dai2/2020,
editor = {Matthew E. Taylor and
Yang Yu and
Edith Elkind and
Yang Gao},
title = {Distributed Artificial Intelligence - Second International Conference,
{DAI} 2020, Nanjing, China, October 24-27, 2020, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {12547},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-3-030-64096-5},
doi = {10.1007/978-3-030-64096-5},
isbn = {978-3-030-64095-8},
timestamp = {Wed, 25 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dai2/2020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-02513,
author = {Sriram Ganapathi Subramanian and
Pascal Poupart and
Matthew E. Taylor and
Nidhi Hegde},
title = {Multi Type Mean Field Reinforcement Learning},
journal = {CoRR},
volume = {abs/2002.02513},
year = {2020},
url = {https://arxiv.org/abs/2002.02513},
eprinttype = {arXiv},
eprint = {2002.02513},
timestamp = {Thu, 23 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-02513.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-04960,
author = {Sanmit Narvekar and
Bei Peng and
Matteo Leonetti and
Jivko Sinapov and
Matthew E. Taylor and
Peter Stone},
title = {Curriculum Learning for Reinforcement Learning Domains: {A} Framework
and Survey},
journal = {CoRR},
volume = {abs/2003.04960},
year = {2020},
url = {https://arxiv.org/abs/2003.04960},
eprinttype = {arXiv},
eprint = {2003.04960},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-04960.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2004-00600,
author = {Craig Sherstan and
Bilal Kartal and
Pablo Hernandez{-}Leal and
Matthew E. Taylor},
title = {Work in Progress: Temporally Extended Auxiliary Tasks},
journal = {CoRR},
volume = {abs/2004.00600},
year = {2020},
url = {https://arxiv.org/abs/2004.00600},
eprinttype = {arXiv},
eprint = {2004.00600},
timestamp = {Wed, 08 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2004-00600.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-01544,
author = {Adam Bignold and
Francisco Cruz and
Matthew E. Taylor and
Tim Brys and
Richard Dazeley and
Peter Vamplew and
Cameron Foale},
title = {A Conceptual Framework for Externally-influenced Agents: An Assisted
Reinforcement Learning Review},
journal = {CoRR},
volume = {abs/2007.01544},
year = {2020},
url = {https://arxiv.org/abs/2007.01544},
eprinttype = {arXiv},
eprint = {2007.01544},
timestamp = {Sat, 23 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-01544.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2009-13736,
author = {Yunshu Du and
Garrett Warnell and
Assefaw Hadish Gebremedhin and
Peter Stone and
Matthew E. Taylor},
title = {Lucid Dreaming for Experience Replay: Refreshing Past States with
the Current Policy},
journal = {CoRR},
volume = {abs/2009.13736},
year = {2020},
url = {https://arxiv.org/abs/2009.13736},
eprinttype = {arXiv},
eprint = {2009.13736},
timestamp = {Wed, 30 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2009-13736.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-03744,
author = {Sai Krishna Gottipati and
Yashaswi Pathak and
Rohan Nuttall and
Sahir and
Raviteja Chunduru and
Ahmed Touati and
Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Sarath Chandar},
title = {Maximum Reward Formulation In Reinforcement Learning},
journal = {CoRR},
volume = {abs/2010.03744},
year = {2020},
url = {https://arxiv.org/abs/2010.03744},
eprinttype = {arXiv},
eprint = {2010.03744},
timestamp = {Tue, 13 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-03744.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-01297,
author = {Paniz Behboudian and
Yash Satsangi and
Matthew E. Taylor and
Anna Harutyunyan and
Michael Bowling},
title = {Useful Policy Invariant Shaping from Arbitrary Advice},
journal = {CoRR},
volume = {abs/2011.01297},
year = {2020},
url = {https://arxiv.org/abs/2011.01297},
eprinttype = {arXiv},
eprint = {2011.01297},
timestamp = {Fri, 06 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-01297.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-15791,
author = {Sriram Ganapathi Subramanian and
Matthew E. Taylor and
Mark Crowley and
Pascal Poupart},
title = {Partially Observable Mean Field Reinforcement Learning},
journal = {CoRR},
volume = {abs/2012.15791},
year = {2020},
url = {https://arxiv.org/abs/2012.15791},
eprinttype = {arXiv},
eprint = {2012.15791},
timestamp = {Fri, 08 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-15791.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/Hernandez-LealK19,
author = {Pablo Hernandez{-}Leal and
Bilal Kartal and
Matthew E. Taylor},
title = {A survey and critique of multiagent deep reinforcement learning},
journal = {Auton. Agents Multi Agent Syst.},
volume = {33},
number = {6},
pages = {750--797},
year = {2019},
url = {https://doi.org/10.1007/s10458-019-09421-1},
doi = {10.1007/S10458-019-09421-1},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/aamas/Hernandez-LealK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cogsr/WilsonPRCGNMSTC19,
author = {Garrett Wilson and
Christopher Pereyda and
Nisha Raghunath and
Gabriel Victor de la Cruz and
Shivam Goel and
Sepehr Nesaei and
Bryan David Minor and
Maureen Schmitter{-}Edgecombe and
Matthew E. Taylor and
Diane J. Cook},
title = {Robot-enabled support of daily activities in smart home environments},
journal = {Cogn. Syst. Res.},
volume = {54},
pages = {258--272},
year = {2019},
url = {https://doi.org/10.1016/j.cogsys.2018.10.032},
doi = {10.1016/J.COGSYS.2018.10.032},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/cogsr/WilsonPRCGNMSTC19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ker/CruzDT19,
author = {Gabriel Victor de la Cruz and
Yunshu Du and
Matthew E. Taylor},
title = {Pre-training with non-expert human demonstration for deep reinforcement
learning},
journal = {Knowl. Eng. Rev.},
volume = {34},
pages = {e10},
year = {2019},
url = {https://doi.org/10.1017/S0269888919000055},
doi = {10.1017/S0269888919000055},
timestamp = {Thu, 27 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ker/CruzDT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ker/BanerjeeVT19,
author = {Bikramjit Banerjee and
Syamala Vittanala and
Matthew Edmund Taylor},
title = {Team learning from human demonstration with coordination confidence},
journal = {Knowl. Eng. Rev.},
volume = {34},
pages = {e12},
year = {2019},
url = {https://doi.org/10.1017/S0269888919000043},
doi = {10.1017/S0269888919000043},
timestamp = {Thu, 27 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ker/BanerjeeVT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/make/FachantidisTV19,
author = {Anestis Fachantidis and
Matthew E. Taylor and
Ioannis P. Vlahavas},
title = {Learning to Teach Reinforcement Learning Agents},
journal = {Mach. Learn. Knowl. Extr.},
volume = {1},
number = {1},
pages = {21--42},
year = {2019},
url = {https://doi.org/10.3390/make1010002},
doi = {10.3390/MAKE1010002},
timestamp = {Thu, 13 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/make/FachantidisTV19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tkde/DuGT19,
author = {Yunshu Du and
Assefaw H. Gebremedhin and
Matthew E. Taylor},
title = {Analysis of University Fitness Center Data Uncovers Interesting Patterns,
Enables Prediction},
journal = {{IEEE} Trans. Knowl. Data Eng.},
volume = {31},
number = {8},
pages = {1478--1490},
year = {2019},
url = {https://doi.org/10.1109/TKDE.2018.2863705},
doi = {10.1109/TKDE.2018.2863705},
timestamp = {Thu, 05 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tkde/DuGT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aiide/GaoKHT19,
author = {Chao Gao and
Bilal Kartal and
Pablo Hernandez{-}Leal and
Matthew E. Taylor},
editor = {Gillian Smith and
Levi Lelis},
title = {On Hard Exploration for Reinforcement Learning: {A} Case Study in
Pommerman},
booktitle = {Proceedings of the Fifteenth {AAAI} Conference on Artificial Intelligence
and Interactive Digital Entertainment, {AIIDE} 2019, October 8-12,
2019, Atlanta, Georgia, {USA}},
pages = {24--30},
publisher = {{AAAI} Press},
year = {2019},
url = {https://ojs.aaai.org/index.php/AIIDE/article/view/5220},
timestamp = {Mon, 07 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aiide/GaoKHT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aiide/Hernandez-LealK19,
author = {Pablo Hernandez{-}Leal and
Bilal Kartal and
Matthew E. Taylor},
editor = {Gillian Smith and
Levi Lelis},
title = {Agent Modeling as Auxiliary Task for Deep Reinforcement Learning},
booktitle = {Proceedings of the Fifteenth {AAAI} Conference on Artificial Intelligence
and Interactive Digital Entertainment, {AIIDE} 2019, October 8-12,
2019, Atlanta, Georgia, {USA}},
pages = {31--37},
publisher = {{AAAI} Press},
year = {2019},
url = {https://ojs.aaai.org/index.php/AIIDE/article/view/5221},
timestamp = {Mon, 07 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aiide/Hernandez-LealK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aiide/KartalHT19,
author = {Bilal Kartal and
Pablo Hernandez{-}Leal and
Matthew E. Taylor},
editor = {Gillian Smith and
Levi Lelis},
title = {Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning},
booktitle = {Proceedings of the Fifteenth {AAAI} Conference on Artificial Intelligence
and Interactive Digital Entertainment, {AIIDE} 2019, October 8-12,
2019, Atlanta, Georgia, {USA}},
pages = {38--44},
publisher = {{AAAI} Press},
year = {2019},
url = {https://ojs.aaai.org/index.php/AIIDE/article/view/5222},
timestamp = {Mon, 07 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aiide/KartalHT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aiide/KartalHT19a,
author = {Bilal Kartal and
Pablo Hernandez{-}Leal and
Matthew E. Taylor},
editor = {Gillian Smith and
Levi Lelis},
title = {Action Guidance with {MCTS} for Deep Reinforcement Learning},
booktitle = {Proceedings of the Fifteenth {AAAI} Conference on Artificial Intelligence
and Interactive Digital Entertainment, {AIIDE} 2019, October 8-12,
2019, Atlanta, Georgia, {USA}},
pages = {153--159},
publisher = {{AAAI} Press},
year = {2019},
url = {https://ojs.aaai.org/index.php/AIIDE/article/view/5238},
timestamp = {Mon, 07 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aiide/KartalHT19a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dai2/WangHWT19,
author = {Weixun Wang and
Jianye Hao and
Yixi Wang and
Matthew E. Taylor},
title = {Achieving cooperation through deep multiagent reinforcement learning
in sequential prisoner's dilemmas},
booktitle = {Proceedings of the First International Conference on Distributed Artificial
Intelligence, {DAI} 2019, Beijing, China, October 13-15, 2019},
pages = {11:1--11:7},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3356464.3357712},
doi = {10.1145/3356464.3357712},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/dai2/WangHWT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/WangT19,
author = {Zhaodong Wang and
Matthew E. Taylor},
editor = {Sarit Kraus},
title = {Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge
from Human and Agent Demonstrations},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16,
2019},
pages = {3820--3827},
publisher = {ijcai.org},
year = {2019},
url = {https://doi.org/10.24963/ijcai.2019/530},
doi = {10.24963/IJCAI.2019/530},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/WangT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/YoungWT19,
author = {Kenny Young and
Baoxiang Wang and
Matthew E. Taylor},
editor = {Sarit Kraus},
title = {Metatrace Actor-Critic: Online Step-Size Tuning by Meta-gradient Descent
for Reinforcement Learning Control},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16,
2019},
pages = {4185--4191},
publisher = {ijcai.org},
year = {2019},
url = {https://doi.org/10.24963/ijcai.2019/581},
doi = {10.24963/IJCAI.2019/581},
timestamp = {Fri, 17 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/YoungWT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tabletop/DouglasYKHMT19,
author = {Nathan Douglas and
Dianna Yim and
Bilal Kartal and
Pablo Hernandez{-}Leal and
Frank Maurer and
Matthew E. Taylor},
editor = {Bongshin Lee and
Geehyuk Lee and
Stacey D. Scott and
Melanie Tory and
Jeonghyun Kim},
title = {Towers of Saliency: {A} Reinforcement Learning Visualization Using
Immersive Environments},
booktitle = {Proceedings of the 2019 {ACM} International Conference on Interactive
Surfaces and Spaces, {ISS} 2019, Daejeon, South Korea, November 10-13,
2019},
pages = {339--342},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3343055.3360747},
doi = {10.1145/3343055.3360747},
timestamp = {Fri, 02 Dec 2022 08:27:05 +0100},
biburl = {https://dblp.org/rec/conf/tabletop/DouglasYKHMT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/atal/2019,
editor = {Edith Elkind and
Manuela Veloso and
Noa Agmon and
Matthew E. Taylor},
title = {Proceedings of the 18th International Conference on Autonomous Agents
and MultiAgent Systems, {AAMAS} '19, Montreal, QC, Canada, May 13-17,
2019},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
year = {2019},
url = {http://dl.acm.org/citation.cfm?id=3306127},
isbn = {978-1-4503-6309-9},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/2019.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-02206,
author = {Gabriel Victor de la Cruz and
Yunshu Du and
Matthew E. Taylor},
title = {Jointly Pre-training with Supervised, Autoencoder, and Value Losses
for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1904.02206},
year = {2019},
url = {http://arxiv.org/abs/1904.02206},
eprinttype = {arXiv},
eprint = {1904.02206},
timestamp = {Wed, 24 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-02206.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-05759,
author = {Bilal Kartal and
Pablo Hernandez{-}Leal and
Chao Gao and
Matthew E. Taylor},
title = {Safer Deep {RL} with Shallow {MCTS:} {A} Case Study in Pommerman},
journal = {CoRR},
volume = {abs/1904.05759},
year = {2019},
url = {http://arxiv.org/abs/1904.05759},
eprinttype = {arXiv},
eprint = {1904.05759},
timestamp = {Thu, 25 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-05759.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-01360,
author = {Chao Gao and
Pablo Hernandez{-}Leal and
Bilal Kartal and
Matthew E. Taylor},
title = {Skynet: {A} Top Deep {RL} Agent in the Inaugural Pommerman Team Competition},
journal = {CoRR},
volume = {abs/1905.01360},
year = {2019},
url = {http://arxiv.org/abs/1905.01360},
eprinttype = {arXiv},
eprint = {1905.01360},
timestamp = {Mon, 27 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-01360.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-08478,
author = {Robert T. Loftin and
Bei Peng and
Matthew E. Taylor and
Michael L. Littman and
David L. Roberts},
title = {Interactive Learning of Environment Dynamics for Sequential Tasks},
journal = {CoRR},
volume = {abs/1907.08478},
year = {2019},
url = {http://arxiv.org/abs/1907.08478},
eprinttype = {arXiv},
eprint = {1907.08478},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-08478.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-09597,
author = {Pablo Hernandez{-}Leal and
Bilal Kartal and
Matthew E. Taylor},
title = {Agent Modeling as Auxiliary Task for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1907.09597},
year = {2019},
url = {http://arxiv.org/abs/1907.09597},
eprinttype = {arXiv},
eprint = {1907.09597},
timestamp = {Tue, 30 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-09597.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-10827,
author = {Bilal Kartal and
Pablo Hernandez{-}Leal and
Matthew E. Taylor},
title = {Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1907.10827},
year = {2019},
url = {http://arxiv.org/abs/1907.10827},
eprinttype = {arXiv},
eprint = {1907.10827},
timestamp = {Thu, 01 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-10827.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-11703,
author = {Bilal Kartal and
Pablo Hernandez{-}Leal and
Matthew E. Taylor},
title = {Action Guidance with {MCTS} for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1907.11703},
year = {2019},
url = {http://arxiv.org/abs/1907.11703},
eprinttype = {arXiv},
eprint = {1907.11703},
timestamp = {Thu, 01 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-11703.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-11788,
author = {Chao Gao and
Bilal Kartal and
Pablo Hernandez{-}Leal and
Matthew E. Taylor},
title = {On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman},
journal = {CoRR},
volume = {abs/1907.11788},
year = {2019},
url = {http://arxiv.org/abs/1907.11788},
eprinttype = {arXiv},
eprint = {1907.11788},
timestamp = {Thu, 01 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-11788.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ker/RosenfeldCTK18,
author = {Ariel Rosenfeld and
Moshe Cohen and
Matthew E. Taylor and
Sarit Kraus},
title = {Leveraging human knowledge in tabular reinforcement learning: a study
of human subjects},
journal = {Knowl. Eng. Rev.},
volume = {33},
pages = {e14},
year = {2018},
url = {https://doi.org/10.1017/S0269888918000206},
doi = {10.1017/S0269888918000206},
timestamp = {Thu, 27 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ker/RosenfeldCTK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tetci/PengMLLRT18,
author = {Bei Peng and
James MacGlashan and
Robert Tyler Loftin and
Michael L. Littman and
David L. Roberts and
Matthew E. Taylor},
title = {Curriculum Design for Machine Learners in Sequential Decision Tasks},
journal = {{IEEE} Trans. Emerg. Top. Comput. Intell.},
volume = {2},
number = {4},
pages = {268--277},
year = {2018},
url = {https://doi.org/10.1109/TETCI.2018.2829980},
doi = {10.1109/TETCI.2018.2829980},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tetci/PengMLLRT18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/SilvaTC18,
author = {Felipe Leno da Silva and
Matthew E. Taylor and
Anna Helena Reali Costa},
editor = {J{\'{e}}r{\^{o}}me Lang},
title = {Autonomously Reusing Knowledge in Multiagent Reinforcement Learning},
booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on
Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm,
Sweden},
pages = {5487--5493},
publisher = {ijcai.org},
year = {2018},
url = {https://doi.org/10.24963/ijcai.2018/774},
doi = {10.24963/IJCAI.2018/774},
timestamp = {Fri, 27 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ijcai/SilvaTC18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/Taylor18,
author = {Matthew E. Taylor},
editor = {J{\'{e}}r{\^{o}}me Lang},
title = {Improving Reinforcement Learning with Human Input},
booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on
Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm,
Sweden},
pages = {5724--5728},
publisher = {ijcai.org},
year = {2018},
url = {https://doi.org/10.24963/ijcai.2018/817},
doi = {10.24963/IJCAI.2018/817},
timestamp = {Tue, 20 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/Taylor18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-00162,
author = {Weixun Wang and
Jianye Hao and
Yixi Wang and
Matthew E. Taylor},
title = {Towards Cooperation in Sequential Prisoner's Dilemmas: a Deep Multiagent
Reinforcement Learning Approach},
journal = {CoRR},
volume = {abs/1803.00162},
year = {2018},
url = {http://arxiv.org/abs/1803.00162},
eprinttype = {arXiv},
eprint = {1803.00162},
timestamp = {Mon, 28 Mar 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-00162.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-04493,
author = {Zhaodong Wang and
Matthew E. Taylor},
title = {Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge
from Human/Agent's Demonstration},
journal = {CoRR},
volume = {abs/1805.04493},
year = {2018},
url = {http://arxiv.org/abs/1805.04493},
eprinttype = {arXiv},
eprint = {1805.04493},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-04493.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-04514,
author = {Kenny Young and
Baoxiang Wang and
Matthew E. Taylor},
title = {Metatrace: Online Step-size Tuning by Meta-gradient Descent for Reinforcement
Learning Control},
journal = {CoRR},
volume = {abs/1805.04514},
year = {2018},
url = {http://arxiv.org/abs/1805.04514},
eprinttype = {arXiv},
eprint = {1805.04514},
timestamp = {Fri, 17 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-04514.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-05769,
author = {Ariel Rosenfeld and
Moshe Cohen and
Matthew E. Taylor and
Sarit Kraus},
title = {Leveraging human knowledge in tabular reinforcement learning: {A}
study of human subjects},
journal = {CoRR},
volume = {abs/1805.05769},
year = {2018},
url = {http://arxiv.org/abs/1805.05769},
eprinttype = {arXiv},
eprint = {1805.05769},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-05769.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-05587,
author = {Pablo Hernandez{-}Leal and
Bilal Kartal and
Matthew E. Taylor},
title = {Is multiagent deep reinforcement learning the answer or the question?
{A} brief survey},
journal = {CoRR},
volume = {abs/1810.05587},
year = {2018},
url = {http://arxiv.org/abs/1810.05587},
eprinttype = {arXiv},
eprint = {1810.05587},
timestamp = {Tue, 30 Oct 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-05587.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-08275,
author = {Behzad Ghazanfari and
Fatemeh Afghah and
Matthew E. Taylor},
title = {Autonomous Extraction of a Hierarchical Structure of Tasks in Reinforcement
Learning, {A} Sequential Associate Rule Mining Approach},
journal = {CoRR},
volume = {abs/1811.08275},
year = {2018},
url = {http://arxiv.org/abs/1811.08275},
eprinttype = {arXiv},
eprint = {1811.08275},
timestamp = {Mon, 26 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-08275.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-00045,
author = {Bilal Kartal and
Pablo Hernandez{-}Leal and
Matthew E. Taylor},
title = {Using Monte Carlo Tree Search as a Demonstrator within Asynchronous
Deep {RL}},
journal = {CoRR},
volume = {abs/1812.00045},
year = {2018},
url = {http://arxiv.org/abs/1812.00045},
eprinttype = {arXiv},
eprint = {1812.00045},
timestamp = {Tue, 01 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-00045.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-08904,
author = {Gabriel Victor de la Cruz and
Yunshu Du and
Matthew E. Taylor},
title = {Pre-training with Non-expert Human Demonstration for Deep Reinforcement
Learning},
journal = {CoRR},
volume = {abs/1812.08904},
year = {2018},
url = {http://arxiv.org/abs/1812.08904},
eprinttype = {arXiv},
eprint = {1812.08904},
timestamp = {Wed, 02 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-08904.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/Hernandez-LealZ17,
author = {Pablo Hernandez{-}Leal and
Yusen Zhan and
Matthew E. Taylor and
Luis Enrique Sucar and
Enrique Munoz de Cote},
title = {Efficiently detecting switches against non-stationary opponents},
journal = {Auton. Agents Multi Agent Syst.},
volume = {31},
number = {4},
pages = {767--789},
year = {2017},
url = {https://doi.org/10.1007/s10458-016-9352-6},
doi = {10.1007/S10458-016-9352-6},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/aamas/Hernandez-LealZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/Hernandez-LealZ17a,
author = {Pablo Hernandez{-}Leal and
Yusen Zhan and
Matthew E. Taylor and
Luis Enrique Sucar and
Enrique Munoz de Cote},
title = {An exploration strategy for non-stationary opponents},
journal = {Auton. Agents Multi Agent Syst.},
volume = {31},
number = {5},
pages = {971--1002},
year = {2017},
url = {https://doi.org/10.1007/s10458-016-9347-3},
doi = {10.1007/S10458-016-9347-3},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/aamas/Hernandez-LealZ17a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijon/BrysHVNT17,
author = {Tim Brys and
Anna Harutyunyan and
Peter Vrancx and
Ann Now{\'{e}} and
Matthew E. Taylor},
title = {Multi-objectivization and ensembles of shapings in reinforcement learning},
journal = {Neurocomputing},
volume = {263},
pages = {48--59},
year = {2017},
url = {https://doi.org/10.1016/j.neucom.2017.02.096},
doi = {10.1016/J.NEUCOM.2017.02.096},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ijon/BrysHVNT17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/neco/ZhanBT17,
author = {Yusen Zhan and
Haitham Bou{-}Ammar and
Matthew E. Taylor},
title = {Nonconvex Policy Search Using Variational Inequalities},
journal = {Neural Comput.},
volume = {29},
number = {10},
pages = {2800--2824},
year = {2017},
url = {https://doi.org/10.1162/neco\_a\_01004},
doi = {10.1162/NECO\_A\_01004},
timestamp = {Tue, 01 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/neco/ZhanBT17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pr/ZhanBT17,
author = {Yusen Zhan and
Haitham Bou{-}Ammar and
Matthew E. Taylor},
title = {Scalable lifelong reinforcement learning},
journal = {Pattern Recognit.},
volume = {72},
pages = {407--418},
year = {2017},
url = {https://doi.org/10.1016/j.patcog.2017.07.031},
doi = {10.1016/J.PATCOG.2017.07.031},
timestamp = {Mon, 24 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/pr/ZhanBT17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/robotics/YeWJHTHZ17,
author = {Yunxiang Ye and
Zhaodong Wang and
Dylan Jones and
Long He and
Matthew E. Taylor and
Geoffrey A. Hollinger and
Qin Zhang},
title = {Bin-Dog: {A} Robotic Platform for Bin Management in Orchards},
journal = {Robotics},
volume = {6},
number = {2},
pages = {12},
year = {2017},
url = {https://doi.org/10.3390/robotics6020012},
doi = {10.3390/ROBOTICS6020012},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/robotics/YeWJHTHZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/BsatBT17,
author = {Salam El Bsat and
Haitham Bou{-}Ammar and
Matthew E. Taylor},
editor = {Satinder Singh and
Shaul Markovitch},
title = {Scalable Multitask Policy Gradient Reinforcement Learning},
booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence,
February 4-9, 2017, San Francisco, California, {USA}},
pages = {1847--1853},
publisher = {{AAAI} Press},
year = {2017},
url = {https://doi.org/10.1609/aaai.v31i1.10942},
doi = {10.1609/AAAI.V31I1.10942},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/BsatBT17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TaylorA17,
author = {Matthew E. Taylor and
Sakire Arslan Ay},
editor = {Satinder Singh and
Shaul Markovitch},
title = {{AI} Projects for Computer Science Capstone Classes (Extended Abstract)},
booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence,
February 4-9, 2017, San Francisco, California, {USA}},
pages = {4819--4821},
publisher = {{AAAI} Press},
year = {2017},
url = {https://doi.org/10.1609/aaai.v31i1.10556},
doi = {10.1609/AAAI.V31I1.10556},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TaylorA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZulasFGT17,
author = {Amanda Leah Zulas and
Kaitlyn I. Franz and
Darrin Griechen and
Matthew E. Taylor},
title = {Solar Decathlon Competition: Towards a Solar-Powered Smart Home},
booktitle = {The Workshops of the The Thirty-First {AAAI} Conference on Artificial
Intelligence, Saturday, February 4-9, 2017, San Francisco, California,
{USA}},
series = {{AAAI} Technical Report},
volume = {{WS-17}},
publisher = {{AAAI} Press},
year = {2017},
url = {http://aaai.org/ocs/index.php/WS/AAAIW17/paper/view/15147},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZulasFGT17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/Hernandez-LealZ17,
author = {Pablo Hernandez{-}Leal and
Yusen Zhan and
Matthew E. Taylor and
Luis Enrique Sucar and
Enrique Munoz de Cote},
editor = {Kate Larson and
Michael Winikoff and
Sanmay Das and
Edmund H. Durfee},
title = {Detecting Switches Against Non-Stationary Opponents},
booktitle = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent
Systems, {AAMAS} 2017, S{\~{a}}o Paulo, Brazil, May 8-12, 2017},
pages = {920--921},
publisher = {{ACM}},
year = {2017},
url = {http://dl.acm.org/citation.cfm?id=3091255},
timestamp = {Wed, 27 Sep 2017 07:24:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/Hernandez-LealZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/Hernandez-LealZ17a,
author = {Pablo Hernandez{-}Leal and
Yusen Zhan and
Matthew E. Taylor and
Luis Enrique Sucar and
Enrique Munoz de Cote},
editor = {Kate Larson and
Michael Winikoff and
Sanmay Das and
Edmund H. Durfee},
title = {An Exploration Strategy Facing Non-Stationary Agents},
booktitle = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent
Systems, {AAMAS} 2017, S{\~{a}}o Paulo, Brazil, May 8-12, 2017},
pages = {922--923},
publisher = {{ACM}},
year = {2017},
url = {http://dl.acm.org/citation.cfm?id=3091256},
timestamp = {Thu, 11 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/Hernandez-LealZ17a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/PengMLLRT17,
author = {Bei Peng and
James MacGlashan and
Robert T. Loftin and
Michael L. Littman and
David L. Roberts and
Matthew E. Taylor},
editor = {Kate Larson and
Michael Winikoff and
Sanmay Das and
Edmund H. Durfee},
title = {Curriculum Design for Machine Learners in Sequential Decision Tasks},
booktitle = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent
Systems, {AAMAS} 2017, S{\~{a}}o Paulo, Brazil, May 8-12, 2017},
pages = {1682--1684},
publisher = {{ACM}},
year = {2017},
url = {http://dl.acm.org/citation.cfm?id=3091403},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/PengMLLRT17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/RosenfeldTK17,
author = {Ariel Rosenfeld and
Matthew E. Taylor and
Sarit Kraus},
editor = {Kate Larson and
Michael Winikoff and
Sanmay Das and
Edmund H. Durfee},
title = {Speeding up Tabular Reinforcement Learning Using State-Action Similarities},
booktitle = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent
Systems, {AAMAS} 2017, S{\~{a}}o Paulo, Brazil, May 8-12, 2017},
pages = {1722--1724},
publisher = {{ACM}},
year = {2017},
url = {http://dl.acm.org/citation.cfm?id=3091417},
timestamp = {Thu, 11 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/RosenfeldTK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MacGlashanHLPWR17,
author = {James MacGlashan and
Mark K. Ho and
Robert Tyler Loftin and
Bei Peng and
Guan Wang and
David L. Roberts and
Matthew E. Taylor and
Michael L. Littman},
editor = {Doina Precup and
Yee Whye Teh},
title = {Interactive Learning from Policy-Dependent Human Feedback},
booktitle = {Proceedings of the 34th International Conference on Machine Learning,
{ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017},
series = {Proceedings of Machine Learning Research},
volume = {70},
pages = {2285--2294},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/macglashan17a.html},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/MacGlashanHLPWR17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/WangT17,
author = {Zhaodong Wang and
Matthew E. Taylor},
editor = {Carles Sierra},
title = {Improving Reinforcement Learning with Confidence-Based Demonstrations},
booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on
Artificial Intelligence, {IJCAI} 2017, Melbourne, Australia, August
19-25, 2017},
pages = {3027--3033},
publisher = {ijcai.org},
year = {2017},
url = {https://doi.org/10.24963/ijcai.2017/422},
doi = {10.24963/IJCAI.2017/422},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/WangT17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/RosenfeldTK17,
author = {Ariel Rosenfeld and
Matthew E. Taylor and
Sarit Kraus},
editor = {Carles Sierra},
title = {Leveraging Human Knowledge in Tabular Reinforcement Learning: {A}
Study of Human Subjects},
booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on
Artificial Intelligence, {IJCAI} 2017, Melbourne, Australia, August
19-25, 2017},
pages = {3823--3830},
publisher = {ijcai.org},
year = {2017},
url = {https://doi.org/10.24963/ijcai.2017/534},
doi = {10.24963/IJCAI.2017/534},
timestamp = {Tue, 20 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/RosenfeldTK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MacGlashanHLPRT17,
author = {James MacGlashan and
Mark K. Ho and
Robert Tyler Loftin and
Bei Peng and
David L. Roberts and
Matthew E. Taylor and
Michael L. Littman},
title = {Interactive Learning from Policy-Dependent Human Feedback},
journal = {CoRR},
volume = {abs/1701.06049},
year = {2017},
url = {http://arxiv.org/abs/1701.06049},
eprinttype = {arXiv},
eprint = {1701.06049},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/MacGlashanHLPRT17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/FachantidisTV17,
author = {Anestis Fachantidis and
Matthew E. Taylor and
Ioannis P. Vlahavas},
title = {Learning to Teach Reinforcement Learning Agents},
journal = {CoRR},
volume = {abs/1707.09079},
year = {2017},
url = {http://arxiv.org/abs/1707.09079},
eprinttype = {arXiv},
eprint = {1707.09079},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/FachantidisTV17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-04083,
author = {Gabriel Victor de la Cruz and
Yunshu Du and
Matthew E. Taylor},
title = {Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement
Learning},
journal = {CoRR},
volume = {abs/1709.04083},
year = {2017},
url = {http://arxiv.org/abs/1709.04083},
eprinttype = {arXiv},
eprint = {1709.04083},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-04083.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-04579,
author = {Behzad Ghazanfari and
Matthew E. Taylor},
title = {Autonomous Extracting a Hierarchical Structure of Tasks in Reinforcement
Learning and Multi-task Reinforcement Learning},
journal = {CoRR},
volume = {abs/1709.04579},
year = {2017},
url = {http://arxiv.org/abs/1709.04579},
eprinttype = {arXiv},
eprint = {1709.04579},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-04579.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/LoftinPMLTHR16,
author = {Robert T. Loftin and
Bei Peng and
James MacGlashan and
Michael L. Littman and
Matthew E. Taylor and
Jeff Huang and
David L. Roberts},
title = {Learning behaviors via human-delivered discrete feedback: modeling
implicit feedback strategies to speed up learning},
journal = {Auton. Agents Multi Agent Syst.},
volume = {30},
number = {1},
pages = {30--59},
year = {2016},
url = {https://doi.org/10.1007/s10458-015-9283-7},
doi = {10.1007/S10458-015-9283-7},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aamas/LoftinPMLTHR16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/Hernandez-LealT16,
author = {Pablo Hernandez{-}Leal and
Matthew E. Taylor and
Benjamin Rosman and
Luis Enrique Sucar and
Enrique Munoz de Cote},
editor = {Stefano V. Albrecht and
Katie Genter and
Somchaya Liemhetcharat},
title = {Identifying and Tracking Switching, Non-Stationary Opponents: {A}
Bayesian Approach},
booktitle = {Multiagent Interaction without Prior Coordination, Papers from the
2016 {AAAI} Workshop, Phoenix, Arizona, USA, February 13, 2016},
series = {{AAAI} Technical Report},
volume = {{WS-16-11}},
publisher = {{AAAI} Press},
year = {2016},
url = {http://www.aaai.org/ocs/index.php/WS/AAAIW16/paper/view/12584},
timestamp = {Tue, 05 Sep 2023 08:59:27 +0200},
biburl = {https://dblp.org/rec/conf/aaai/Hernandez-LealT16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaifs/CurranBATS16,
author = {William Curran and
Tim Brys and
David W. Aha and
Matthew E. Taylor and
William D. Smart},
title = {Dimensionality Reduced Reinforcement Learning for Assistive Robots},
booktitle = {2016 {AAAI} Fall Symposia, Arlington, Virginia, USA, November 17-19,
2016},
publisher = {{AAAI} Press},
year = {2016},
url = {http://aaai.org/ocs/index.php/FSS/FSS16/paper/view/14076},
timestamp = {Thu, 15 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaaifs/CurranBATS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaifs/LoftinMPTLR16,
author = {Robert Tyler Loftin and
James MacGlashan and
Bei Peng and
Matthew E. Taylor and
Michael L. Littman and
David L. Roberts},
title = {Towards Behavior-Aware Model Learning from Human-Generated Trajectories},
booktitle = {2016 {AAAI} Fall Symposia, Arlington, Virginia, USA, November 17-19,
2016},
publisher = {{AAAI} Press},
year = {2016},
url = {http://aaai.org/ocs/index.php/FSS/FSS16/paper/view/14094},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaaifs/LoftinMPTLR16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaiss/WangT16,
author = {Zhaodong Wang and
Matthew E. Taylor},
title = {Effective Transfer via Demonstrations in Reinforcement Learning: {A}
Preliminary Study},
booktitle = {2016 {AAAI} Spring Symposia, Stanford University, Palo Alto, California,
USA, March 21-23, 2016},
publisher = {{AAAI} Press},
year = {2016},
url = {http://www.aaai.org/ocs/index.php/SSS/SSS16/paper/view/12739},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaaiss/WangT16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SuayBTC16,
author = {Halit Bener Suay and
Tim Brys and
Matthew E. Taylor and
Sonia Chernova},
editor = {Catholijn M. Jonker and
Stacy Marsella and
John Thangarajah and
Karl Tuyls},
title = {Learning from Demonstration for Shaping through Inverse Reinforcement
Learning},
booktitle = {Proceedings of the 2016 International Conference on Autonomous Agents
{\&} Multiagent Systems, Singapore, May 9-13, 2016},
pages = {429--437},
publisher = {{ACM}},
year = {2016},
url = {http://dl.acm.org/citation.cfm?id=2936988},
timestamp = {Fri, 20 May 2016 20:33:29 +0200},
biburl = {https://dblp.org/rec/conf/atal/SuayBTC16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/PengMLLRT16,
author = {Bei Peng and
James MacGlashan and
Robert Tyler Loftin and
Michael L. Littman and
David L. Roberts and
Matthew E. Taylor},
editor = {Catholijn M. Jonker and
Stacy Marsella and
John Thangarajah and
Karl Tuyls},
title = {A Need for Speed: Adapting Agent Action Speed to Improve Task Learning
from Non-Expert Humans},
booktitle = {Proceedings of the 2016 International Conference on Autonomous Agents
{\&} Multiagent Systems, Singapore, May 9-13, 2016},
pages = {957--965},
publisher = {{ACM}},
year = {2016},
url = {http://dl.acm.org/citation.cfm?id=2937065},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/PengMLLRT16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/Hernandez-LealR16,
author = {Pablo Hernandez{-}Leal and
Benjamin Rosman and
Matthew E. Taylor and
Luis Enrique Sucar and
Enrique Munoz de Cote},
editor = {Catholijn M. Jonker and
Stacy Marsella and
John Thangarajah and
Karl Tuyls},
title = {A Bayesian Approach for Learning and Tracking Switching, Non-Stationary
Opponents: (Extended Abstract)},
booktitle = {Proceedings of the 2016 International Conference on Autonomous Agents
{\&} Multiagent Systems, Singapore, May 9-13, 2016},
pages = {1315--1316},
publisher = {{ACM}},
year = {2016},
url = {http://dl.acm.org/citation.cfm?id=2937137},
timestamp = {Fri, 20 May 2016 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/Hernandez-LealR16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/ZhanBT16,
author = {Yusen Zhan and
Haitham Bou{-}Ammar and
Matthew E. Taylor},
editor = {Subbarao Kambhampati},
title = {Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement
Learning Settings with Applications to Negative Transfer},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI} 2016, New York, NY, USA, 9-15 July
2016},
pages = {2315--2321},
publisher = {{IJCAI/AAAI} Press},
year = {2016},
url = {http://www.ijcai.org/Abstract/16/330},
timestamp = {Tue, 20 Aug 2019 16:19:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/ZhanBT16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/IseleLECIKT16,
author = {David Isele and
Jos{\'{e}}{-}Marcio Luna and
Eric Eaton and
Gabriel Victor de la Cruz and
James Irwin and
Brandon Kallaher and
Matthew E. Taylor},
title = {Lifelong learning for disturbance rejection on mobile robots},
booktitle = {2016 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, {IROS} 2016, Daejeon, South Korea, October 9-14, 2016},
pages = {3993--3998},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/IROS.2016.7759588},
doi = {10.1109/IROS.2016.7759588},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iros/IseleLECIKT16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhanAT16,
author = {Yusen Zhan and
Haitham Bou{-}Ammar and
Matthew E. Taylor},
title = {Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement
Learning Settings with Applications to Negative Transfer},
journal = {CoRR},
volume = {abs/1604.03986},
year = {2016},
url = {http://arxiv.org/abs/1604.03986},
eprinttype = {arXiv},
eprint = {1604.03986},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhanAT16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/adb/FachantidisPTV15,
author = {Anestis Fachantidis and
Ioannis Partalas and
Matthew E. Taylor and
Ioannis P. Vlahavas},
title = {Transfer learning with probabilistic mapping selection},
journal = {Adapt. Behav.},
volume = {23},
number = {1},
pages = {3--19},
year = {2015},
url = {https://doi.org/10.1177/1059712314559525},
doi = {10.1177/1059712314559525},
timestamp = {Tue, 25 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/adb/FachantidisPTV15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/Bou-AmmarERT15,
author = {Haitham Bou{-}Ammar and
Eric Eaton and
Paul Ruvolo and
Matthew E. Taylor},
editor = {Blai Bonet and
Sven Koenig},
title = {Unsupervised Cross-Domain Transfer in Policy Gradient Reinforcement
Learning via Manifold Alignment},
booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence,
January 25-30, 2015, Austin, Texas, {USA}},
pages = {2504--2510},
publisher = {{AAAI} Press},
year = {2015},
url = {https://doi.org/10.1609/aaai.v29i1.9631},
doi = {10.1609/AAAI.V29I1.9631},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/Bou-AmmarERT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/CruzPLT15,
author = {Gabriel Victor de la Cruz and
Bei Peng and
Walter Stephen Lasecki and
Matthew Edmund Taylor},
editor = {Michael Bowling and
Marc G. Bellemare and
Erik Talvitie and
Joel Veness and
Marlos C. Machado},
title = {Generating Real-Time Crowd Advice to Improve Reinforcement Learning
Agents},
booktitle = {Learning for General Competency in Video Games, Papers from the 2015
{AAAI} Workshop, Austin, Texas, USA, January 26, 2015},
series = {{AAAI} Technical Report},
volume = {{WS-15-10}},
publisher = {{AAAI} Press},
year = {2015},
url = {http://aaai.org/ocs/index.php/WS/AAAIW15/paper/view/9947},
timestamp = {Tue, 05 Sep 2023 08:59:27 +0200},
biburl = {https://dblp.org/rec/conf/aaai/CruzPLT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaifs/ZhanT15,
author = {Yusen Zhan and
Matthew E. Taylor},
title = {Online Transfer Learning in Reinforcement Learning Domains},
booktitle = {2015 {AAAI} Fall Symposia, Arlington, Virginia, USA, November 12-14,
2015},
pages = {97},
publisher = {{AAAI} Press},
year = {2015},
url = {http://www.aaai.org/ocs/index.php/FSS/FSS15/paper/view/11646},
timestamp = {Wed, 14 Nov 2018 16:20:12 +0100},
biburl = {https://dblp.org/rec/conf/aaaifs/ZhanT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaifs/ScottPCNPMT15,
author = {Mitchell Scott and
Bei Peng and
Madeline Chili and
Tanay Nigam and
Francis G. Pascual and
Cynthia Matuszek and
Matthew E. Taylor},
title = {On the Ability to Provide Demonstrations on a {UAS:} Observing 90
Untrained Participants Abusing a Flying Robot},
booktitle = {2015 {AAAI} Fall Symposia, Arlington, Virginia, USA, November 12-14,
2015},
pages = {117--121},
publisher = {{AAAI} Press},
year = {2015},
url = {http://www.aaai.org/ocs/index.php/FSS/FSS15/paper/view/11677},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaaifs/ScottPCNPMT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/BrysHTN15,
author = {Tim Brys and
Anna Harutyunyan and
Matthew E. Taylor and
Ann Now{\'{e}}},
editor = {Gerhard Weiss and
Pinar Yolum and
Rafael H. Bordini and
Edith Elkind},
title = {Policy Transfer using Reward Shaping},
booktitle = {Proceedings of the 2015 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2015, Istanbul, Turkey, May 4-8, 2015},
pages = {181--188},
publisher = {{ACM}},
year = {2015},
url = {http://dl.acm.org/citation.cfm?id=2772905},
timestamp = {Tue, 08 Mar 2022 10:12:47 +0100},
biburl = {https://dblp.org/rec/conf/atal/BrysHTN15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/Hernandez-LealT15,
author = {Pablo Hernandez{-}Leal and
Matthew E. Taylor and
Enrique Munoz de Cote and
Luis Enrique Sucar},
editor = {Gerhard Weiss and
Pinar Yolum and
Rafael H. Bordini and
Edith Elkind},
title = {Bidding in Non-Stationary Energy Markets},
booktitle = {Proceedings of the 2015 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2015, Istanbul, Turkey, May 4-8, 2015},
pages = {1709--1710},
publisher = {{ACM}},
year = {2015},
url = {http://dl.acm.org/citation.cfm?id=2773397},
timestamp = {Fri, 15 May 2015 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/Hernandez-LealT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/BrysHSCTN15,
author = {Tim Brys and
Anna Harutyunyan and
Halit Bener Suay and
Sonia Chernova and
Matthew E. Taylor and
Ann Now{\'{e}}},
editor = {Qiang Yang and
Michael J. Wooldridge},
title = {Reinforcement Learning from Demonstration through Shaping},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI} 2015, Buenos Aires, Argentina, July
25-31, 2015},
pages = {3352--3358},
publisher = {{AAAI} Press},
year = {2015},
url = {http://ijcai.org/Abstract/15/472},
timestamp = {Tue, 20 Aug 2019 16:16:43 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/BrysHSCTN15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iui/CruzPLT15,
author = {Gabriel Victor de la Cruz and
Bei Peng and
Walter S. Lasecki and
Matthew E. Taylor},
editor = {Oliver Brdiczka and
Polo Chau and
Giuseppe Carenini and
Shimei Pan and
Per Ola Kristensson},
title = {Towards Integrating Real-Time Crowd Advice with Reinforcement Learning},
booktitle = {Proceedings of the 20th International Conference on Intelligent User
Interfaces Companion, {IUI} 2015, Atlanta, GA, USA, March 29 - April
01, 2015},
pages = {17--20},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2732158.2732180},
doi = {10.1145/2732158.2732180},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iui/CruzPLT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/CurranBTS15,
author = {William Curran and
Tim Brys and
Matthew E. Taylor and
William D. Smart},
title = {Using {PCA} to Efficiently Represent State Spaces},
journal = {CoRR},
volume = {abs/1505.00322},
year = {2015},
url = {http://arxiv.org/abs/1505.00322},
eprinttype = {arXiv},
eprint = {1505.00322},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/CurranBTS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhanT15,
author = {Yusen Zhan and
Matthew E. Taylor},
title = {Online Transfer Learning in Reinforcement Learning Domains},
journal = {CoRR},
volume = {abs/1507.00436},
year = {2015},
url = {http://arxiv.org/abs/1507.00436},
eprinttype = {arXiv},
eprint = {1507.00436},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhanT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/connection/TaylorCFVT14,
author = {Matthew E. Taylor and
Nicholas Carboni and
Anestis Fachantidis and
Ioannis P. Vlahavas and
Lisa Torrey},
title = {Reinforcement learning agents providing advice in complex video games},
journal = {Connect. Sci.},
volume = {26},
number = {1},
pages = {45--63},
year = {2014},
url = {https://doi.org/10.1080/09540091.2014.885279},
doi = {10.1080/09540091.2014.885279},
timestamp = {Sun, 02 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/connection/TaylorCFVT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/connection/BrysPT14,
author = {Tim Brys and
Tong T. Pham and
Matthew E. Taylor},
title = {Distributed learning and multi-objectivity in traffic light control},
journal = {Connect. Sci.},
volume = {26},
number = {1},
pages = {65--83},
year = {2014},
url = {https://doi.org/10.1080/09540091.2014.885282},
doi = {10.1080/09540091.2014.885282},
timestamp = {Thu, 15 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/connection/BrysPT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/LoftinMPTLHR14,
author = {Robert Tyler Loftin and
James MacGlashan and
Bei Peng and
Matthew E. Taylor and
Michael L. Littman and
Jeff Huang and
David L. Roberts},
editor = {Carla E. Brodley and
Peter Stone},
title = {A Strategy-Aware Technique for Learning Behaviors from Discrete Human
Feedback},
booktitle = {Proceedings of the Twenty-Eighth {AAAI} Conference on Artificial Intelligence,
July 27 -31, 2014, Qu{\'{e}}bec City, Qu{\'{e}}bec, Canada},
pages = {937--943},
publisher = {{AAAI} Press},
year = {2014},
url = {https://doi.org/10.1609/aaai.v28i1.8839},
doi = {10.1609/AAAI.V28I1.8839},
timestamp = {Mon, 04 Sep 2023 15:06:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/LoftinMPTLHR14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/BrysNKT14,
author = {Tim Brys and
Ann Now{\'{e}} and
Daniel Kudenko and
Matthew E. Taylor},
editor = {Carla E. Brodley and
Peter Stone},
title = {Combining Multiple Correlated Reward and Shaping Signals by Measuring
Confidence},
booktitle = {Proceedings of the Twenty-Eighth {AAAI} Conference on Artificial Intelligence,
July 27 -31, 2014, Qu{\'{e}}bec City, Qu{\'{e}}bec, Canada},
pages = {1687--1693},
publisher = {{AAAI} Press},
year = {2014},
url = {https://doi.org/10.1609/aaai.v28i1.8998},
doi = {10.1609/AAAI.V28I1.8998},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/BrysNKT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/BrysMNT14,
author = {Tim Brys and
Kristof Van Moffaert and
Ann Now{\'{e}} and
Matthew E. Taylor},
editor = {Ana L. C. Bazzan and
Michael N. Huhns and
Alessio Lomuscio and
Paul Scerri},
title = {Adaptive objective selection for correlated objectives in multi-objective
reinforcement learning},
booktitle = {International conference on Autonomous Agents and Multi-Agent Systems,
{AAMAS} '14, Paris, France, May 5-9, 2014},
pages = {1349--1350},
publisher = {{IFAAMAS/ACM}},
year = {2014},
url = {http://dl.acm.org/citation.cfm?id=2617467},
timestamp = {Thu, 25 Sep 2014 07:46:15 +0200},
biburl = {https://dblp.org/rec/conf/atal/BrysMNT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/HolmesParkerTAT14,
author = {Chris HolmesParker and
Matthew E. Taylor and
Adrian K. Agogino and
Kagan Tumer},
editor = {Ana L. C. Bazzan and
Michael N. Huhns and
Alessio Lomuscio and
Paul Scerri},
title = {CLEANing the reward: counterfactual actions to remove exploratory
action noise in multiagent learning (extended abstract)},
booktitle = {International conference on Autonomous Agents and Multi-Agent Systems,
{AAMAS} '14, Paris, France, May 5-9, 2014},
pages = {1353--1354},
publisher = {{IFAAMAS/ACM}},
year = {2014},
url = {http://dl.acm.org/citation.cfm?id=2617469},
timestamp = {Thu, 25 Sep 2014 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/HolmesParkerTAT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecai/BrysTN14,
author = {Tim Brys and
Matthew E. Taylor and
Ann Now{\'{e}}},
editor = {Torsten Schaub and
Gerhard Friedrich and
Barry O'Sullivan},
title = {Using Ensemble Techniques and Multi-Objectivization to Solve Reinforcement
Learning Problems},
booktitle = {{ECAI} 2014 - 21st European Conference on Artificial Intelligence,
18-22 August 2014, Prague, Czech Republic - Including Prestigious
Applications of Intelligent Systems {(PAIS} 2014)},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {263},
pages = {981--982},
publisher = {{IOS} Press},
year = {2014},
url = {https://doi.org/10.3233/978-1-61499-419-0-981},
doi = {10.3233/978-1-61499-419-0-981},
timestamp = {Mon, 19 Jun 2023 16:36:09 +0200},
biburl = {https://dblp.org/rec/conf/ecai/BrysTN14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/Bou-AmmarERT14,
author = {Haitham Bou{-}Ammar and
Eric Eaton and
Paul Ruvolo and
Matthew E. Taylor},
title = {Online Multi-Task Learning for Policy Gradient Methods},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {1206--1214},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/ammar14.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/Bou-AmmarERT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/BrysHVTKN14,
author = {Tim Brys and
Anna Harutyunyan and
Peter Vrancx and
Matthew E. Taylor and
Daniel Kudenko and
Ann Now{\'{e}}},
title = {Multi-objectivization of reinforcement learning problems by reward
shaping},
booktitle = {2014 International Joint Conference on Neural Networks, {IJCNN} 2014,
Beijing, China, July 6-11, 2014},
pages = {2315--2322},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/IJCNN.2014.6889732},
doi = {10.1109/IJCNN.2014.6889732},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/BrysHVTKN14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/TaylorT14,
author = {Matthew E. Taylor and
Lisa Torrey},
editor = {Toon Calders and
Floriana Esposito and
Eyke H{\"{u}}llermeier and
Rosa Meo},
title = {Agents Teaching Agents in Reinforcement Learning (Nectar Abstract)},
booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference,
{ECML} {PKDD} 2014, Nancy, France, September 15-19, 2014. Proceedings,
Part {III}},
series = {Lecture Notes in Computer Science},
volume = {8726},
pages = {524--528},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-662-44845-8\_50},
doi = {10.1007/978-3-662-44845-8\_50},
timestamp = {Thu, 31 Oct 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pkdd/TaylorT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ro-man/LoftinPMLTHR14,
author = {Robert Tyler Loftin and
Bei Peng and
James MacGlashan and
Michael L. Littman and
Matthew E. Taylor and
Jeff Huang and
David L. Roberts},
title = {Learning something from nothing: Leveraging implicit human feedback
strategies},
booktitle = {The 23rd {IEEE} International Symposium on Robot and Human Interactive
Communication, {IEEE} {RO-MAN} 2014, Edinburgh, UK, August 25-29,
2014},
pages = {607--612},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ROMAN.2014.6926319},
doi = {10.1109/ROMAN.2014.6926319},
timestamp = {Sun, 18 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ro-man/LoftinPMLTHR14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/setn/FachantidisPTV14,
author = {Anestis Fachantidis and
Ioannis Partalas and
Matthew E. Taylor and
Ioannis P. Vlahavas},
editor = {Aristidis Likas and
Konstantinos Blekas and
Dimitris Kalles},
title = {An Autonomous Transfer Learning Algorithm for TD-Learners},
booktitle = {Artificial Intelligence: Methods and Applications - 8th Hellenic Conference
on AI, {SETN} 2014, Ioannina, Greece, May 15-17, 2014. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {8445},
pages = {57--70},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-319-07064-3\_5},
doi = {10.1007/978-3-319-07064-3\_5},
timestamp = {Sun, 02 Oct 2022 16:15:01 +0200},
biburl = {https://dblp.org/rec/conf/setn/FachantidisPTV14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/webi/HolmesParkerTAT14,
author = {Chris HolmesParker and
Matthew E. Taylor and
Adrian K. Agogino and
Kagan Tumer},
title = {{CLEAN} Rewards to Improve Coordination by Removing Exploratory Action
Noise},
booktitle = {2014 {IEEE/WIC/ACM} International Joint Conferences on Web Intelligence
{(WI)} and Intelligent Agent Technologies (IAT), Warsaw, Poland, August
11-14, 2014 - Volume {III}},
pages = {127--134},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/WI-IAT.2014.159},
doi = {10.1109/WI-IAT.2014.159},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/webi/HolmesParkerTAT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/adhoc/VieiraTTJGST13,
author = {Marcos Augusto M. Vieira and
Matthew E. Taylor and
Prateek Tandon and
Manish Jain and
Ramesh Govindan and
Gaurav S. Sukhatme and
Milind Tambe},
title = {Mitigating multi-path fading in a mobile mesh network},
journal = {Ad Hoc Networks},
volume = {11},
number = {4},
pages = {1510--1521},
year = {2013},
url = {https://doi.org/10.1016/j.adhoc.2011.01.014},
doi = {10.1016/J.ADHOC.2011.01.014},
timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/adhoc/VieiraTTJGST13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaiss/BalasubramanianT13,
author = {Ravi Balasubramanian and
Matthew E. Taylor},
title = {Learning for Mobile-Robot Error Recovery (Extended Abstract)},
booktitle = {Designing Intelligent Robots: Reintegrating {AI} II, Papers from the
2013 {AAAI} Spring Symposium, Palo Alto, California, USA, March 25-27,
2013},
series = {{AAAI} Technical Report},
volume = {{SS-13-04}},
publisher = {{AAAI}},
year = {2013},
url = {http://www.aaai.org/ocs/index.php/SSS/SSS13/paper/view/5710},
timestamp = {Mon, 09 Sep 2013 15:13:13 +0200},
biburl = {https://dblp.org/rec/conf/aaaiss/BalasubramanianT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaiss/FachantidisPTV13,
author = {Anestis Fachantidis and
Ioannis Partalas and
Matthew E. Taylor and
Ioannis P. Vlahavas},
title = {Autonomous Selection of Inter-Task Mappings in Transfer Learning (extended
abstract)},
booktitle = {Lifelong Machine Learning, Papers from the 2013 {AAAI} Spring Symposium,
Palo Alto, California, USA, March 25-27, 2013},
series = {{AAAI} Technical Report},
volume = {{SS-13-05}},
publisher = {{AAAI}},
year = {2013},
url = {http://www.aaai.org/ocs/index.php/SSS/SSS13/paper/view/5751},
timestamp = {Mon, 09 Sep 2013 15:11:14 +0200},
biburl = {https://dblp.org/rec/conf/aaaiss/FachantidisPTV13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TorreyT13,
author = {Lisa Torrey and
Matthew E. Taylor},
editor = {Maria L. Gini and
Onn Shehory and
Takayuki Ito and
Catholijn M. Jonker},
title = {Teaching on a budget: agents advising agents in reinforcement learning},
booktitle = {International conference on Autonomous Agents and Multi-Agent Systems,
{AAMAS} '13, Saint Paul, MN, USA, May 6-10, 2013},
pages = {1053--1060},
publisher = {{IFAAMAS}},
year = {2013},
url = {http://dl.acm.org/citation.cfm?id=2485086},
timestamp = {Thu, 09 Sep 2021 16:09:54 +0200},
biburl = {https://dblp.org/rec/conf/atal/TorreyT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/Bou-AmmarMTDTW13,
author = {Haitham Bou{-}Ammar and
Decebal Constantin Mocanu and
Matthew E. Taylor and
Kurt Driessens and
Karl Tuyls and
Gerhard Weiss},
editor = {Hendrik Blockeel and
Kristian Kersting and
Siegfried Nijssen and
Filip Zelezn{\'{y}}},
title = {Automatically Mapped Transfer between Reinforcement Learning Tasks
via Three-Way Restricted Boltzmann Machines},
booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference,
{ECML} {PKDD} 2013, Prague, Czech Republic, September 23-27, 2013,
Proceedings, Part {II}},
series = {Lecture Notes in Computer Science},
volume = {8189},
pages = {449--464},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-642-40991-2\_29},
doi = {10.1007/978-3-642-40991-2\_29},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pkdd/Bou-AmmarMTDTW13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aamas/Bou-AmmarTTDW12,
author = {Haitham Bou{-}Ammar and
Karl Tuyls and
Matthew E. Taylor and
Kurt Driessens and
Gerhard Weiss},
editor = {Wiebe van der Hoek and
Lin Padgham and
Vincent Conitzer and
Michael Winikoff},
title = {Reinforcement learning transfer via sparse coding},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems,
{AAMAS} 2012, Valencia, Spain, June 4-8, 2012 {(3} Volumes)},
pages = {383--390},
publisher = {{IFAAMAS}},
year = {2012},
url = {http://dl.acm.org/citation.cfm?id=2343631},
timestamp = {Tue, 08 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aamas/Bou-AmmarTTDW12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aamas/TorreyT12,
author = {Lisa Torrey and
Matthew E. Taylor},
editor = {Wiebe van der Hoek and
Lin Padgham and
Vincent Conitzer and
Michael Winikoff},
title = {Towards student/teacher learning in sequential decision tasks},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems,
{AAMAS} 2012, Valencia, Spain, June 4-8, 2012 {(3} Volumes)},
pages = {1383--1384},
publisher = {{IFAAMAS}},
year = {2012},
url = {http://dl.acm.org/citation.cfm?id=2344018},
timestamp = {Thu, 19 Mar 2015 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aamas/TorreyT12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/advcs/SchweitzerT11,
author = {Frank Schweitzer and
Matthew E. Taylor},
title = {Editorial: Agents and Multi-Agent Systems},
journal = {Adv. Complex Syst.},
volume = {14},
number = {2},
year = {2011},
url = {https://doi.org/10.1142/S0219525911003025},
doi = {10.1142/S0219525911003025},
timestamp = {Thu, 08 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/advcs/SchweitzerT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/advcs/TaylorJTYT11,
author = {Matthew E. Taylor and
Manish Jain and
Prateek Tandon and
Makoto Yokoo and
Milind Tambe},
title = {Distributed on-Line Multi-Agent Optimization under Uncertainty: Balancing
Exploration and Exploitation},
journal = {Adv. Complex Syst.},
volume = {14},
number = {3},
pages = {471--528},
year = {2011},
url = {https://doi.org/10.1142/S0219525911003104},
doi = {10.1142/S0219525911003104},
timestamp = {Thu, 09 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/advcs/TaylorJTYT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aim/TaylorS11,
author = {Matthew E. Taylor and
Peter Stone},
title = {An Introduction to Intertask Transfer for Reinforcement Learning},
journal = {{AI} Mag.},
volume = {32},
number = {1},
pages = {15--34},
year = {2011},
url = {https://doi.org/10.1609/aimag.v32i1.2329},
doi = {10.1609/AIMAG.V32I1.2329},
timestamp = {Tue, 25 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aim/TaylorS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaiss/TaylorSC11,
author = {Matthew Edmund Taylor and
Halit Bener Suay and
Sonia Chernova},
title = {Using Human Demonstrations to Improve Reinforcement Learning},
booktitle = {Help Me Help You: Bridging the Gaps in Human-Agent Collaboration,
Papers from the 2011 {AAAI} Spring Symposium, Technical Report SS-11-05,
Stanford, California, USA, March 21-23, 2011},
publisher = {{AAAI}},
year = {2011},
url = {http://www.aaai.org/ocs/index.php/SSS/SSS11/paper/view/2384},
timestamp = {Tue, 14 Feb 2012 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaaiss/TaylorSC11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/adprl/WhitesonTTS11,
author = {Shimon Whiteson and
Brian Tanner and
Matthew E. Taylor and
Peter Stone},
title = {Protecting against evaluation overfitting in empirical reinforcement
learning},
booktitle = {2011 {IEEE} Symposium on Adaptive Dynamic Programming And Reinforcement
Learning, {ADPRL} 2011, Paris, France, April 12-14, 2011},
pages = {120--127},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ADPRL.2011.5967363},
doi = {10.1109/ADPRL.2011.5967363},
timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
biburl = {https://dblp.org/rec/conf/adprl/WhitesonTTS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/Bou-AmmarT11,
author = {Haitham Bou{-}Ammar and
Matthew E. Taylor},
editor = {Peter Vrancx and
Matthew Knudson and
Marek Grzes},
title = {Reinforcement Learning Transfer via Common Subspaces},
booktitle = {Adaptive and Learning Agents - International Workshop, {ALA} 2011,
Held at {AAMAS} 2011, Taipei, Taiwan, May 2, 2011, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {7113},
pages = {21--36},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-28499-1\_2},
doi = {10.1007/978-3-642-28499-1\_2},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/atal/Bou-AmmarT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ScerriKVMSTDFCDK11,
author = {Paul Scerri and
Balajee Kannan and
Prasanna Velagapudi and
Kate Macarthur and
Peter Stone and
Matthew E. Taylor and
John Dolan and
Alessandro Farinelli and
Archie C. Chapman and
Bernadine Dias and
George Kantor},
editor = {Francien Dechesne and
Hiromitsu Hattori and
Adriaan ter Mors and
Jose M. Such and
Danny Weyns and
Frank Dignum},
title = {Flood Disaster Mitigation: {A} Real-World Challenge Problem for Multi-agent
Unmanned Surface Vehicles},
booktitle = {Advanced Agent Technology - {AAMAS} 2011 Workshops, AMPLE, AOSE, ARMS,
DOCM3AS, ITMAS, Taipei, Taiwan, May 2-6, 2011. Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {7068},
pages = {252--269},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-27216-5\_16},
doi = {10.1007/978-3-642-27216-5\_16},
timestamp = {Mon, 15 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/ScerriKVMSTDFCDK11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TsaiFBBEKMORSTWZT11,
author = {Jason Tsai and
Natalie Fridman and
Emma Bowring and
Matthew Brown and
Shira Epstein and
Gal A. Kaminka and
Stacy Marsella and
Andrew Ogden and
Inbal Rika and
Ankur Sheel and
Matthew E. Taylor and
Xuezhi Wang and
Avishay Zilka and
Milind Tambe},
editor = {Liz Sonenberg and
Peter Stone and
Kagan Tumer and
Pinar Yolum},
title = {{ESCAPES:} evacuation simulation with children, authorities, parents,
emotions, and social comparison},
booktitle = {10th International Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2011), Taipei, Taiwan, May 2-6, 2011, Volume 1-3},
pages = {457--464},
publisher = {{IFAAMAS}},
year = {2011},
url = {http://portal.acm.org/citation.cfm?id=2031682\&\#38;CFID=54178199\&\#38;CFTOKEN=61392764},
timestamp = {Wed, 15 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/TsaiFBBEKMORSTWZT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TaylorSC11,
author = {Matthew E. Taylor and
Halit Bener Suay and
Sonia Chernova},
editor = {Liz Sonenberg and
Peter Stone and
Kagan Tumer and
Pinar Yolum},
title = {Integrating reinforcement learning with human demonstrations of varying
ability},
booktitle = {10th International Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2011), Taipei, Taiwan, May 2-6, 2011, Volume 1-3},
pages = {617--624},
publisher = {{IFAAMAS}},
year = {2011},
url = {http://portal.acm.org/citation.cfm?id=2031705\&\#38;CFID=54178199\&\#38;CFTOKEN=61392764},
timestamp = {Fri, 18 Nov 2011 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/TaylorSC11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TaylorKS11,
author = {Matthew E. Taylor and
Brian Kulis and
Fei Sha},
editor = {Liz Sonenberg and
Peter Stone and
Kagan Tumer and
Pinar Yolum},
title = {Metric learning for reinforcement learning agents},
booktitle = {10th International Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2011), Taipei, Taiwan, May 2-6, 2011, Volume 1-3},
pages = {777--784},
publisher = {{IFAAMAS}},
year = {2011},
url = {http://portal.acm.org/citation.cfm?id=2031728\&\#38;CFID=54178199\&\#38;CFTOKEN=61392764},
timestamp = {Fri, 18 Nov 2011 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/TaylorKS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/KwakYYTT11,
author = {Jun{-}young Kwak and
Rong Yang and
Zhengyu Yin and
Matthew E. Taylor and
Milind Tambe},
editor = {Liz Sonenberg and
Peter Stone and
Kagan Tumer and
Pinar Yolum},
title = {Teamwork in distributed POMDPs: execution-time coordination under
model uncertainty},
booktitle = {10th International Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2011), Taipei, Taiwan, May 2-6, 2011, Volume 1-3},
pages = {1261--1262},
publisher = {{IFAAMAS}},
year = {2011},
url = {http://portal.acm.org/citation.cfm?id=2034516\&\#38;CFID=69154334\&\#38;CFTOKEN=45298625},
timestamp = {Fri, 18 Nov 2011 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/KwakYYTT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eaai/Taylor11,
author = {Matthew Edmund Taylor},
editor = {Marie desJardins},
title = {Teaching Reinforcement Learning with Mario: An Argument and Case Study},
booktitle = {Second Symposium on Education Advances in Artificial Intelligence,
{EAAI} 2011, San Francisco, CA, USA, August 7-11, 2011},
pages = {1737--1742},
publisher = {{AAAI} Press},
year = {2011},
url = {https://doi.org/10.1609/aaai.v25i3.18841},
doi = {10.1609/AAAI.V25I3.18841},
timestamp = {Thu, 14 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eaai/Taylor11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eaai/Nellerd0T11,
author = {Todd W. Neller and
Marie desJardins and
Tim Oates and
Matthew E. Taylor},
editor = {Marie desJardins},
title = {Model {AI} Assignments 2011},
booktitle = {Second Symposium on Education Advances in Artificial Intelligence,
{EAAI} 2011, San Francisco, CA, USA, August 7-11, 2011},
pages = {1746},
publisher = {{AAAI} Press},
year = {2011},
url = {https://doi.org/10.1609/aaai.v25i3.18843},
doi = {10.1609/AAAI.V25I3.18843},
timestamp = {Thu, 14 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eaai/Nellerd0T11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eumas/Bou-AmmarTTW11,
author = {Haitham Bou{-}Ammar and
Matthew E. Taylor and
Karl Tuyls and
Gerhard Weiss},
editor = {Massimo Cossentino and
Michael Kaisers and
Karl Tuyls and
Gerhard Weiss},
title = {Reinforcement Learning Transfer Using a Sparse Coded Inter-task Mapping},
booktitle = {Multi-Agent Systems - 9th European Workshop, {EUMAS} 2011, Maastricht,
The Netherlands, November 14-15, 2011. Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {7541},
pages = {1--16},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-34799-3\_1},
doi = {10.1007/978-3-642-34799-3\_1},
timestamp = {Tue, 08 Mar 2022 10:12:48 +0100},
biburl = {https://dblp.org/rec/conf/eumas/Bou-AmmarTTW11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/FachantidisPTV11,
author = {Anestis Fachantidis and
Ioannis Partalas and
Matthew E. Taylor and
Ioannis P. Vlahavas},
editor = {Scott Sanner and
Marcus Hutter},
title = {Transfer Learning via Multiple Inter-task Mappings},
booktitle = {Recent Advances in Reinforcement Learning - 9th European Workshop,
{EWRL} 2011, Athens, Greece, September 9-11, 2011, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {7188},
pages = {225--236},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-29946-9\_23},
doi = {10.1007/978-3-642-29946-9\_23},
timestamp = {Sun, 02 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/FachantidisPTV11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iat/KwakYYTT11,
author = {Jun{-}young Kwak and
Rong Yang and
Zhengyu Yin and
Matthew E. Taylor and
Milind Tambe},
editor = {Olivier Boissier and
Jeffrey Bradshaw and
Longbing Cao and
Klaus Fischer and
Mohand{-}Said Hacid},
title = {Towards Addressing Model Uncertainty: Robust Execution-Time Coordination
for Teamwork},
booktitle = {Proceedings of the 2011 {IEEE/WIC/ACM} International Conference on
Intelligent Agent Technology, {IAT} 2011, Campus Scientifique de la
Doua, Lyon, France, August 22-27, 2011},
pages = {204--207},
publisher = {{IEEE} Computer Society},
year = {2011},
url = {https://doi.org/10.1109/WI-IAT.2011.82},
doi = {10.1109/WI-IAT.2011.82},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iat/KwakYYTT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/WhitesonTS10,
author = {Shimon Whiteson and
Matthew E. Taylor and
Peter Stone},
title = {Critical factors in the empirical performance of temporal difference
and evolutionary methods for reinforcement learning},
journal = {Auton. Agents Multi Agent Syst.},
volume = {21},
number = {1},
pages = {1--35},
year = {2010},
url = {https://doi.org/10.1007/s10458-009-9100-2},
doi = {10.1007/S10458-009-9100-2},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/aamas/WhitesonTS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/informaticaSI/TaylorKWT10,
author = {Matthew E. Taylor and
Christopher Kiekintveld and
Craig Western and
Milind Tambe},
title = {A Framework for Evaluating Deployed Security Systems: Is There a Chink
in your ARMOR?},
journal = {Informatica (Slovenia)},
volume = {34},
number = {2},
pages = {129--140},
year = {2010},
url = {http://www.informatica.si/index.php/informatica/article/view/284},
timestamp = {Tue, 16 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/informaticaSI/TaylorKWT10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/KwakYYTT10,
author = {Jun{-}young Kwak and
Rong Yang and
Zhengyu Yin and
Matthew E. Taylor and
Milind Tambe},
title = {Teamwork and Coordination under Model Uncertainty in DEC-POMDPs},
booktitle = {Interactive Decision Theory and Game Theory, Papers from the 2010
{AAAI} Workshop, Atlanta, Georgia, USA, July 12, 2010},
series = {{AAAI} Technical Report},
volume = {{WS-10-03}},
publisher = {{AAAI}},
year = {2010},
url = {http://aaai.org/ocs/index.php/WS/AAAIW10/paper/view/1982},
timestamp = {Tue, 05 Sep 2023 08:59:27 +0200},
biburl = {https://dblp.org/rec/conf/aaai/KwakYYTT10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TaylorCRMBM10,
author = {Matthew E. Taylor and
Katherine E. Coons and
Behnam Robatmili and
Bertrand A. Maher and
Doug Burger and
Kathryn S. McKinley},
editor = {Maria Fox and
David Poole},
title = {Evolving Compiler Heuristics to Manage Communication and Contention},
booktitle = {Proceedings of the Twenty-Fourth {AAAI} Conference on Artificial Intelligence,
{AAAI} 2010, Atlanta, Georgia, USA, July 11-15, 2010},
pages = {1690--1693},
publisher = {{AAAI} Press},
year = {2010},
url = {https://doi.org/10.1609/aaai.v24i1.7711},
doi = {10.1609/AAAI.V24I1.7711},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TaylorCRMBM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TaylorJJYT10,
author = {Matthew E. Taylor and
Manish Jain and
Yanquin Jin and
Makoto Yokoo and
Milind Tambe},
editor = {Wiebe van der Hoek and
Gal A. Kaminka and
Yves Lesp{\'{e}}rance and
Michael Luck and
Sandip Sen},
title = {When should there be a "Me" in "Team"?: distributed
multi-agent optimization under uncertainty},
booktitle = {9th International Conference on Autonomous Agents and Multiagent Systems
{(AAMAS} 2010), Toronto, Canada, May 10-14, 2010, Volume 1-3},
pages = {109--116},
publisher = {{IFAAMAS}},
year = {2010},
url = {https://dl.acm.org/citation.cfm?id=1838222},
timestamp = {Fri, 30 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/TaylorJJYT10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/atal/2009ala,
editor = {Matthew E. Taylor and
Karl Tuyls},
title = {Adaptive and Learning Agents, Second Workshop, {ALA} 2009, Held as
Part of the {AAMAS} 2009 Conference in Budapest, Hungary, May 12,
2009, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {5924},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-11814-2},
doi = {10.1007/978-3-642-11814-2},
isbn = {978-3-642-11813-5},
timestamp = {Tue, 14 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/2009ala.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@book{DBLP:series/sci/2009-216,
author = {Matthew E. Taylor},
title = {Transfer in Reinforcement Learning Domains},
series = {Studies in Computational Intelligence},
volume = {216},
publisher = {Springer},
year = {2009},
url = {https://doi.org/10.1007/978-3-642-01882-4},
doi = {10.1007/978-3-642-01882-4},
isbn = {978-3-642-01881-7},
timestamp = {Tue, 16 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/series/sci/2009-216.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aim/BunescuCCCCDDDFGGGHJJKKKLLMMMMPPRRSSSATWSWZ09,
author = {Razvan C. Bunescu and
Vitor R. Carvalho and
Jan Chomicki and
Vincent Conitzer and
Michael T. Cox and
Virginia Dignum and
Zachary Dodds and
Mark Dredze and
David Furcy and
Evgeniy Gabrilovich and
Mehmet H. G{\"{o}}ker and
Hans W. Guesgen and
Haym Hirsh and
Dietmar Jannach and
Ulrich Junker and
Wolfgang Ketter and
Alfred Kobsa and
Sven Koenig and
Tessa A. Lau and
Lundy Lewis and
Eric T. Matson and
Ted Metzler and
Rada Mihalcea and
Bamshad Mobasher and
Joelle Pineau and
Pascal Poupart and
Anita Raja and
Wheeler Ruml and
Norman M. Sadeh and
Guy Shani and
Daniel G. Shapiro and
Sarabjot Singh Anand and
Matthew E. Taylor and
Kiri Wagstaff and
Trey Smith and
William E. Walsh and
Rong Zhou},
title = {{AAAI} 2008 Workshop Reports},
journal = {{AI} Mag.},
volume = {30},
number = {1},
pages = {108--118},
year = {2009},
url = {https://doi.org/10.1609/aimag.v30i1.2196},
doi = {10.1609/AIMAG.V30I1.2196},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/aim/BunescuCCCCDDDFGGGHJJKKKLLMMMMPPRRSSSATWSWZ09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/TaylorS09,
author = {Matthew E. Taylor and
Peter Stone},
title = {Transfer Learning for Reinforcement Learning Domains: {A} Survey},
journal = {J. Mach. Learn. Res.},
volume = {10},
pages = {1633--1685},
year = {2009},
url = {https://dl.acm.org/doi/10.5555/1577069.1755839},
doi = {10.5555/1577069.1755839},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/TaylorS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaiss/Taylor09,
author = {Matthew E. Taylor},
title = {Assisting Transfer-Enabled Machine Learning Algorithms: Leveraging
Human Knowledge for Curriculum Design},
booktitle = {Agents that Learn from Human Teachers, Papers from the 2009 {AAAI}
Spring Symposium, Technical Report SS-09-01, Stanford, California,
USA, March 23-25, 2009},
pages = {141--143},
publisher = {{AAAI}},
year = {2009},
url = {http://www.aaai.org/Library/Symposia/Spring/2009/ss09-01-020.php},
timestamp = {Fri, 17 Feb 2012 13:45:07 +0100},
biburl = {https://dblp.org/rec/conf/aaaiss/Taylor09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aips/VarakanthamKTMST09,
author = {Pradeep Varakantham and
Jun{-}young Kwak and
Matthew E. Taylor and
Janusz Marecki and
Paul Scerri and
Milind Tambe},
editor = {Alfonso Gerevini and
Adele E. Howe and
Amedeo Cesta and
Ioannis Refanidis},
title = {Exploiting Coordination Locales in Distributed POMDPs via Social Model
Shaping},
booktitle = {Proceedings of the 19th International Conference on Automated Planning
and Scheduling, {ICAPS} 2009, Thessaloniki, Greece, September 19-23,
2009},
publisher = {{AAAI}},
year = {2009},
url = {http://aaai.org/ocs/index.php/ICAPS/ICAPS09/paper/view/733},
timestamp = {Thu, 13 Dec 2012 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aips/VarakanthamKTMST09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/PonsenTT09,
author = {Marc J. V. Ponsen and
Matthew E. Taylor and
Karl Tuyls},
editor = {Matthew E. Taylor and
Karl Tuyls},
title = {Abstraction and Generalization in Reinforcement Learning: {A} Summary
and Framework},
booktitle = {Adaptive and Learning Agents, Second Workshop, {ALA} 2009, Held as
Part of the {AAMAS} 2009 Conference in Budapest, Hungary, May 12,
2009, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {5924},
pages = {1--32},
publisher = {Springer},
year = {2009},
url = {https://doi.org/10.1007/978-3-642-11814-2\_1},
doi = {10.1007/978-3-642-11814-2\_1},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/atal/PonsenTT09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/JainTTY09,
author = {Manish Jain and
Matthew E. Taylor and
Milind Tambe and
Makoto Yokoo},
editor = {Craig Boutilier},
title = {DCOPs Meet the Real World: Exploring Unknown Reward Matrices with
Applications to Mobile Sensor Networks},
booktitle = {{IJCAI} 2009, Proceedings of the 21st International Joint Conference
on Artificial Intelligence, Pasadena, California, USA, July 11-17,
2009},
pages = {181--186},
year = {2009},
url = {http://ijcai.org/Proceedings/09/Papers/040.pdf},
timestamp = {Tue, 20 Aug 2019 16:16:40 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/JainTTY09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEpact/CoonsRTMBM08,
author = {Katherine E. Coons and
Behnam Robatmili and
Matthew E. Taylor and
Bertrand A. Maher and
Doug Burger and
Kathryn S. McKinley},
editor = {Andreas Moshovos and
David Tarditi and
Kunle Olukotun},
title = {Feature selection and policy optimization for distributed instruction
placement using reinforcement learning},
booktitle = {17th International Conference on Parallel Architectures and Compilation
Techniques, {PACT} 2008, Toronto, Ontario, Canada, October 25-29,
2008},
pages = {32--42},
publisher = {{ACM}},
year = {2008},
url = {https://doi.org/10.1145/1454115.1454122},
doi = {10.1145/1454115.1454122},
timestamp = {Wed, 11 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/IEEEpact/CoonsRTMBM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/agi/TaylorKS08,
author = {Matthew E. Taylor and
Gregory Kuhlmann and
Peter Stone},
editor = {Pei Wang and
Ben Goertzel and
Stan Franklin},
title = {Transfer Learning and Intelligence: an Argument and Approach},
booktitle = {Artificial General Intelligence 2008, Proceedings of the First {AGI}
Conference, {AGI} 2008, March 1-3, 2008, University of Memphis, Memphis,
TN, {USA}},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {171},
pages = {326--337},
publisher = {{IOS} Press},
year = {2008},
url = {http://www.booksonline.iospress.nl/Content/View.aspx?piid=8319},
timestamp = {Thu, 24 Aug 2017 11:33:04 +0200},
biburl = {https://dblp.org/rec/conf/agi/TaylorKS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TaylorKS08,
author = {Matthew E. Taylor and
Gregory Kuhlmann and
Peter Stone},
editor = {Lin Padgham and
David C. Parkes and
J{\"{o}}rg P. M{\"{u}}ller and
Simon Parsons},
title = {Autonomous transfer for reinforcement learning},
booktitle = {7th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2008), Estoril, Portugal, May 12-16, 2008, Volume
1},
pages = {283--290},
publisher = {{IFAAMAS}},
year = {2008},
url = {https://dl.acm.org/citation.cfm?id=1402427},
timestamp = {Fri, 30 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/TaylorKS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/TaylorJS08,
author = {Matthew E. Taylor and
Nicholas K. Jong and
Peter Stone},
editor = {Walter Daelemans and
Bart Goethals and
Katharina Morik},
title = {Transferring Instances for Model-Based Reinforcement Learning},
booktitle = {Machine Learning and Knowledge Discovery in Databases, European Conference,
{ECML/PKDD} 2008, Antwerp, Belgium, September 15-19, 2008, Proceedings,
Part {II}},
series = {Lecture Notes in Computer Science},
volume = {5212},
pages = {488--505},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87481-2\_32},
doi = {10.1007/978-3-540-87481-2\_32},
timestamp = {Tue, 14 May 2019 10:00:47 +0200},
biburl = {https://dblp.org/rec/conf/pkdd/TaylorJS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/adb/WhitesonTS07,
author = {Shimon Whiteson and
Matthew E. Taylor and
Peter Stone},
title = {Empirical Studies in Action Selection with Reinforcement Learning},
journal = {Adapt. Behav.},
volume = {15},
number = {1},
pages = {33--50},
year = {2007},
url = {https://doi.org/10.1177/1059712306076253},
doi = {10.1177/1059712306076253},
timestamp = {Tue, 25 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/adb/WhitesonTS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/TaylorSL07,
author = {Matthew E. Taylor and
Peter Stone and
Yaxin Liu},
title = {Transfer Learning via Inter-Task Mappings for Temporal Difference
Learning},
journal = {J. Mach. Learn. Res.},
volume = {8},
pages = {2125--2167},
year = {2007},
url = {https://dl.acm.org/doi/10.5555/1314498.1314569},
doi = {10.5555/1314498.1314569},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/TaylorSL07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TaylorWS07,
author = {Matthew E. Taylor and
Shimon Whiteson and
Peter Stone},
title = {Temporal Difference and Policy Search Methods for Reinforcement Learning:
An Empirical Comparison},
booktitle = {Proceedings of the Twenty-Second {AAAI} Conference on Artificial Intelligence,
July 22-26, 2007, Vancouver, British Columbia, Canada},
pages = {1675--1678},
publisher = {{AAAI} Press},
year = {2007},
url = {http://www.aaai.org/Library/AAAI/2007/aaai07-271.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TaylorWS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TaylorS07,
author = {Matthew E. Taylor and
Peter Stone},
title = {Representation Transfer via Elaboration},
booktitle = {Proceedings of the Twenty-Second {AAAI} Conference on Artificial Intelligence,
July 22-26, 2007, Vancouver, British Columbia, Canada},
pages = {1906--1907},
publisher = {{AAAI} Press},
year = {2007},
url = {http://www.aaai.org/Library/AAAI/2007/aaai07-328.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TaylorS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/Taylor07,
author = {Matthew E. Taylor},
title = {Autonomous Inter-Task Transfer in Reinforcement Learning Domains},
booktitle = {Proceedings of the Twenty-Second {AAAI} Conference on Artificial Intelligence,
July 22-26, 2007, Vancouver, British Columbia, Canada},
pages = {1951--1952},
publisher = {{AAAI} Press},
year = {2007},
url = {http://www.aaai.org/Library/AAAI/2007/aaai07-350.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/Taylor07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaifs/TaylorS07,
author = {Matthew E. Taylor and
Peter Stone},
editor = {Clayton T. Morrison and
Tim Oates},
title = {Representation Transfer for Reinforcement Learning},
booktitle = {Computational Approaches to Representation Change during Learning
and Development, Papers from the 2007 {AAAI} Fall Symposium, Arlington,
Virginia, USA, November 9-11, 2007},
series = {{AAAI} Technical Report},
volume = {{FS-07-03}},
pages = {78--85},
publisher = {{AAAI} Press},
year = {2007},
url = {https://www.aaai.org/Library/Symposia/Fall/2007/fs07-03-015.php},
timestamp = {Sun, 16 Oct 2022 14:19:55 +0200},
biburl = {https://dblp.org/rec/conf/aaaifs/TaylorS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TaylorWS07,
author = {Matthew E. Taylor and
Shimon Whiteson and
Peter Stone},
editor = {Edmund H. Durfee and
Makoto Yokoo and
Michael N. Huhns and
Onn Shehory},
title = {Transfer via inter-task mappings in policy search reinforcement learning},
booktitle = {6th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2007), Honolulu, Hawaii, USA, May 14-18, 2007},
pages = {37},
publisher = {{IFAAMAS}},
year = {2007},
url = {https://doi.org/10.1145/1329125.1329170},
doi = {10.1145/1329125.1329170},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/TaylorWS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TaylorS07,
author = {Matthew E. Taylor and
Peter Stone},
editor = {Edmund H. Durfee and
Makoto Yokoo and
Michael N. Huhns and
Onn Shehory},
title = {Towards reinforcement learning representation transfer},
booktitle = {6th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2007), Honolulu, Hawaii, USA, May 14-18, 2007},
pages = {100},
publisher = {{IFAAMAS}},
year = {2007},
url = {https://doi.org/10.1145/1329125.1329248},
doi = {10.1145/1329125.1329248},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/TaylorS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/AhmadiTS07,
author = {Mazda Ahmadi and
Matthew E. Taylor and
Peter Stone},
editor = {Edmund H. Durfee and
Makoto Yokoo and
Michael N. Huhns and
Onn Shehory},
title = {{IFSA:} incremental feature-set augmentation for reinforcement learning
tasks},
booktitle = {6th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2007), Honolulu, Hawaii, USA, May 14-18, 2007},
pages = {186},
publisher = {{IFAAMAS}},
year = {2007},
url = {https://doi.org/10.1145/1329125.1329351},
doi = {10.1145/1329125.1329351},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/AhmadiTS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/flairs/TaylorMKW07,
author = {Matthew E. Taylor and
Cynthia Matuszek and
Bryan Klimt and
Michael Witbrock},
editor = {David Wilson and
Geoff Sutcliffe},
title = {Autonomous Classification of Knowledge into an Ontology},
booktitle = {Proceedings of the Twentieth International Florida Artificial Intelligence
Research Society Conference, May 7-9, 2007, Key West, Florida, {USA}},
pages = {140--145},
publisher = {{AAAI} Press},
year = {2007},
url = {http://www.aaai.org/Library/FLAIRS/2007/flairs07-026.php},
timestamp = {Tue, 18 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/flairs/TaylorMKW07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/flairs/TaylorMSW07,
author = {Matthew E. Taylor and
Cynthia Matuszek and
Pace Reagan Smith and
Michael Witbrock},
editor = {David Wilson and
Geoff Sutcliffe},
title = {Guiding Inference with Policy Search Reinforcement Learning},
booktitle = {Proceedings of the Twentieth International Florida Artificial Intelligence
Research Society Conference, May 7-9, 2007, Key West, Florida, {USA}},
pages = {146--151},
publisher = {{AAAI} Press},
year = {2007},
url = {http://www.aaai.org/Library/FLAIRS/2007/flairs07-027.php},
timestamp = {Tue, 18 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/flairs/TaylorMSW07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/TaylorS07,
author = {Matthew E. Taylor and
Peter Stone},
editor = {Zoubin Ghahramani},
title = {Cross-domain transfer for reinforcement learning},
booktitle = {Machine Learning, Proceedings of the Twenty-Fourth International Conference
{(ICML} 2007), Corvallis, Oregon, USA, June 20-24, 2007},
series = {{ACM} International Conference Proceeding Series},
volume = {227},
pages = {879--886},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1273496.1273607},
doi = {10.1145/1273496.1273607},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/TaylorS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TaylorS06,
author = {Matthew E. Taylor and
Peter Stone},
title = {Inter-Task Action Correlation for Reinforcement Learning Tasks},
booktitle = {Proceedings, The Twenty-First National Conference on Artificial Intelligence
and the Eighteenth Innovative Applications of Artificial Intelligence
Conference, July 16-20, 2006, Boston, Massachusetts, {USA}},
pages = {1901--1903},
publisher = {{AAAI} Press},
year = {2006},
url = {http://www.aaai.org/Library/AAAI/2006/aaai06-329.php},
timestamp = {Tue, 05 Sep 2023 09:10:47 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TaylorS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gecco/TaylorWS06,
author = {Matthew E. Taylor and
Shimon Whiteson and
Peter Stone},
editor = {Mike Cattolico},
title = {Comparing evolutionary and temporal difference methods in a reinforcement
learning domain},
booktitle = {Genetic and Evolutionary Computation Conference, {GECCO} 2006, Proceedings,
Seattle, Washington, USA, July 8-12, 2006},
pages = {1321--1328},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1143997.1144202},
doi = {10.1145/1143997.1144202},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/gecco/TaylorWS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TaylorSL05,
author = {Matthew E. Taylor and
Peter Stone and
Yaxin Liu},
editor = {Manuela M. Veloso and
Subbarao Kambhampati},
title = {Value Functions for RL-Based Behavior Transfer: {A} Comparative Study},
booktitle = {Proceedings, The Twentieth National Conference on Artificial Intelligence
and the Seventeenth Innovative Applications of Artificial Intelligence
Conference, July 9-13, 2005, Pittsburgh, Pennsylvania, {USA}},
pages = {880--885},
publisher = {{AAAI} Press / The {MIT} Press},
year = {2005},
url = {http://www.aaai.org/Library/AAAI/2005/aaai05-139.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TaylorSL05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TaylorS05,
author = {Matthew E. Taylor and
Peter Stone},
editor = {Frank Dignum and
Virginia Dignum and
Sven Koenig and
Sarit Kraus and
Munindar P. Singh and
Michael J. Wooldridge},
title = {Behavior transfer for value-function-based reinforcement learning},
booktitle = {4th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2005), July 25-29, 2005, Utrecht, The Netherlands},
pages = {53--59},
publisher = {{ACM}},
year = {2005},
url = {https://doi.org/10.1145/1082473.1082482},
doi = {10.1145/1082473.1082482},
timestamp = {Fri, 26 Apr 2019 14:26:42 +0200},
biburl = {https://dblp.org/rec/conf/atal/TaylorS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/StoneKTL05,
author = {Peter Stone and
Gregory Kuhlmann and
Matthew E. Taylor and
Yaxin Liu},
editor = {Ansgar Bredenfeld and
Adam Jacoff and
Itsuki Noda and
Yasutake Takahashi},
title = {Keepaway Soccer: From Machine Learning Testbed to Benchmark},
booktitle = {RoboCup 2005: Robot Soccer World Cup {IX}},
series = {Lecture Notes in Computer Science},
volume = {4020},
pages = {93--105},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/11780519\_9},
doi = {10.1007/11780519\_9},
timestamp = {Tue, 20 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/robocup/StoneKTL05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-04-25 01:44 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
