Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Kavosh Asadi
@inproceedings{DBLP:conf/aistats/GottesmanAAL0L23, author = {Omer Gottesman and Kavosh Asadi and Cameron S. Allen and Samuel Lobel and George Konidaris and Michael Littman}, editor = {Francisco J. R. Ruiz and Jennifer G. Dy and Jan{-}Willem van de Meent}, title = {Coarse-Grained Smoothness for Reinforcement Learning in Metric Spaces}, booktitle = {International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain}, series = {Proceedings of Machine Learning Research}, volume = {206}, pages = {1390--1410}, publisher = {{PMLR}}, year = {2023}, url = {https://proceedings.mlr.press/v206/gottesman23a.html}, timestamp = {Mon, 09 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aistats/GottesmanAAL0L23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/AsadiFS23, author = {Kavosh Asadi and Rasool Fakoor and Shoham Sabach}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, title = {Resetting the Optimizer in Deep {RL:} An Empirical Study}, 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/e4bf5c3245fd92a4554a16af9803b757-Abstract-Conference.html}, timestamp = {Fri, 01 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/AsadiFS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/AsadiS0GF23, author = {Kavosh Asadi and Shoham Sabach and Yao Liu and Omer Gottesman and Rasool Fakoor}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, title = {{TD} Convergence: An Optimization Perspective}, 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/9a08fbb992f15faa695c42b6a2c8e000-Abstract-Conference.html}, timestamp = {Fri, 01 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/AsadiS0GF23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-17750, author = {Kavosh Asadi and Shoham Sabach and Yao Liu and Omer Gottesman and Rasool Fakoor}, title = {{TD} Convergence: An Optimization Perspective}, journal = {CoRR}, volume = {abs/2306.17750}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.17750}, doi = {10.48550/ARXIV.2306.17750}, eprinttype = {arXiv}, eprint = {2306.17750}, timestamp = {Mon, 03 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-17750.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-17833, author = {Kavosh Asadi and Rasool Fakoor and Shoham Sabach}, title = {Resetting the Optimizer in Deep {RL:} An Empirical Study}, journal = {CoRR}, volume = {abs/2306.17833}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.17833}, doi = {10.48550/ARXIV.2306.17833}, eprinttype = {arXiv}, eprint = {2306.17833}, timestamp = {Mon, 03 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-17833.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2310-05905, author = {Zuxin Liu and Jesse Zhang and Kavosh Asadi and Yao Liu and Ding Zhao and Shoham Sabach and Rasool Fakoor}, title = {{TAIL:} Task-specific Adapters for Imitation Learning with Large Pretrained Models}, journal = {CoRR}, volume = {abs/2310.05905}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2310.05905}, doi = {10.48550/ARXIV.2310.05905}, eprinttype = {arXiv}, eprint = {2310.05905}, timestamp = {Tue, 24 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2310-05905.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/AsadiFGKLS22, author = {Kavosh Asadi and Rasool Fakoor and Omer Gottesman and Taesup Kim and Michael L. Littman and Alexander J. Smola}, editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh}, title = {Faster Deep Reinforcement Learning with Slower Online Network}, 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/7dfa77fcef807c9a078b58fd619ad897-Abstract-Conference.html}, timestamp = {Mon, 08 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/AsadiFGKLS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/KlissarovFMAKS22, author = {Martin Klissarov and Rasool Fakoor and Jonas W. Mueller and Kavosh Asadi and Taesup Kim and Alexander J. Smola}, editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh}, title = {Adaptive Interest for Emphatic Reinforcement Learning}, 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/008079ec00eec9760ee93af5434ee932-Abstract-Conference.html}, timestamp = {Mon, 08 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/KlissarovFMAKS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-05588, author = {Zhiyuan Zhou and Cameron Allen and Kavosh Asadi and George Konidaris}, title = {Characterizing the Action-Generalization Gap in Deep Q-Learning}, journal = {CoRR}, volume = {abs/2205.05588}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.05588}, doi = {10.48550/ARXIV.2205.05588}, eprinttype = {arXiv}, eprint = {2205.05588}, timestamp = {Tue, 17 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-05588.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@phdthesis{DBLP:phd/us/Asadi21, author = {Kavosh Asadi}, title = {Smoothness in Reinforcement Learning with Large State and Action Spaces}, school = {Brown University, {USA}}, year = {2021}, url = {https://cs.brown.edu/research/pubs/theses/phd/2021/asadi.kavosh.pdf}, timestamp = {Tue, 28 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/phd/us/Asadi21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/AsadiPPKL21, author = {Kavosh Asadi and Neev Parikh and Ronald E. Parr and George Dimitri Konidaris and Michael L. Littman}, title = {Deep Radial-Basis Value Functions for Continuous Control}, 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 = {6696--6704}, publisher = {{AAAI} Press}, year = {2021}, url = {https://doi.org/10.1609/aaai.v35i8.16828}, doi = {10.1609/AAAI.V35I8.16828}, timestamp = {Mon, 04 Sep 2023 12:29:24 +0200}, biburl = {https://dblp.org/rec/conf/aaai/AsadiPPKL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/LecarpentierAAJ21, author = {Erwan Lecarpentier and David Abel and Kavosh Asadi and Yuu Jinnai and Emmanuel Rachelson and Michael L. Littman}, title = {Lipschitz Lifelong Reinforcement Learning}, 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 = {8270--8278}, publisher = {{AAAI} Press}, year = {2021}, url = {https://doi.org/10.1609/aaai.v35i9.17006}, doi = {10.1609/AAAI.V35I9.17006}, timestamp = {Mon, 04 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aaai/LecarpentierAAJ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/FakoorMACS21, author = {Rasool Fakoor and Jonas Mueller and Kavosh Asadi and Pratik Chaudhari and Alexander J. Smola}, editor = {Marc'Aurelio Ranzato and Alina Beygelzimer and Yann N. Dauphin and Percy Liang and Jennifer Wortman Vaughan}, title = {Continuous Doubly Constrained Batch Reinforcement Learning}, booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual}, pages = {11260--11273}, year = {2021}, url = {https://proceedings.neurips.cc/paper/2021/hash/5da713a690c067105aeb2fae32403405-Abstract.html}, timestamp = {Wed, 19 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/nips/FakoorMACS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2109-07054, author = {Ishaan Shah and David Halpern and Kavosh Asadi and Michael L. Littman}, title = {Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback}, journal = {CoRR}, volume = {abs/2109.07054}, year = {2021}, url = {https://arxiv.org/abs/2109.07054}, eprinttype = {arXiv}, eprint = {2109.07054}, timestamp = {Wed, 22 Sep 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2109-07054.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-12276, author = {Omer Gottesman and Kavosh Asadi and Cameron Allen and Sam Lobel and George Konidaris and Michael Littman}, title = {Coarse-Grained Smoothness for {RL} in Metric Spaces}, journal = {CoRR}, volume = {abs/2110.12276}, year = {2021}, url = {https://arxiv.org/abs/2110.12276}, eprinttype = {arXiv}, eprint = {2110.12276}, timestamp = {Mon, 09 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-12276.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2112-05848, author = {Kavosh Asadi and Rasool Fakoor and Omer Gottesman and Michael L. Littman and Alexander J. Smola}, title = {Deep Q-Network with Proximal Iteration}, journal = {CoRR}, volume = {abs/2112.05848}, year = {2021}, url = {https://arxiv.org/abs/2112.05848}, eprinttype = {arXiv}, eprint = {2112.05848}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2112-05848.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-05411, author = {Erwan Lecarpentier and David Abel and Kavosh Asadi and Yuu Jinnai and Emmanuel Rachelson and Michael L. Littman}, title = {Lipschitz Lifelong Reinforcement Learning}, journal = {CoRR}, volume = {abs/2001.05411}, year = {2020}, url = {https://arxiv.org/abs/2001.05411}, eprinttype = {arXiv}, eprint = {2001.05411}, timestamp = {Fri, 17 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-05411.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-01883, author = {Kavosh Asadi and Ronald E. Parr and George Dimitri Konidaris and Michael L. Littman}, title = {Deep {RBF} Value Functions for Continuous Control}, journal = {CoRR}, volume = {abs/2002.01883}, year = {2020}, url = {https://arxiv.org/abs/2002.01883}, eprinttype = {arXiv}, eprint = {2002.01883}, timestamp = {Mon, 10 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-01883.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-05518, author = {Kavosh Asadi and David Abel and Michael Littman}, title = {Learning State Abstractions for Transfer in Continuous Control}, journal = {CoRR}, volume = {abs/2002.05518}, year = {2020}, url = {https://arxiv.org/abs/2002.05518}, eprinttype = {arXiv}, eprint = {2002.05518}, timestamp = {Mon, 09 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-05518.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/AbelAAJLW19, author = {David Abel and Dilip Arumugam and Kavosh Asadi and Yuu Jinnai and Michael L. Littman and Lawson L. S. Wong}, title = {State Abstraction as Compression in Apprenticeship Learning}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, pages = {3134--3142}, publisher = {{AAAI} Press}, year = {2019}, url = {https://doi.org/10.1609/aaai.v33i01.33013134}, doi = {10.1609/AAAI.V33I01.33013134}, timestamp = {Mon, 04 Sep 2023 12:29:24 +0200}, biburl = {https://dblp.org/rec/conf/aaai/AbelAAJLW19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/atal/KimALK19, author = {Seungchan Kim and Kavosh Asadi and Michael L. Littman and George Dimitri Konidaris}, editor = {Edith Elkind and Manuela Veloso and Noa Agmon and Matthew E. Taylor}, title = {Removing the Target Network from Deep Q-Networks with the Mellowmax Operator}, booktitle = {Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, {AAMAS} '19, Montreal, QC, Canada, May 13-17, 2019}, pages = {2060--2062}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, year = {2019}, url = {http://dl.acm.org/citation.cfm?id=3332010}, timestamp = {Tue, 19 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/atal/KimALK19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcai/KimALK19, author = {Seungchan Kim and Kavosh Asadi and Michael L. Littman and George Dimitri Konidaris}, editor = {Sarit Kraus}, title = {DeepMellow: Removing the Need for a Target Network in Deep Q-Learning}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, pages = {2733--2739}, publisher = {ijcai.org}, year = {2019}, url = {https://doi.org/10.24963/ijcai.2019/379}, doi = {10.24963/IJCAI.2019/379}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ijcai/KimALK19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1905-13320, author = {Kavosh Asadi and Dipendra Misra and Seungchan Kim and Michael L. Littman}, title = {Combating the Compounding-Error Problem with a Multi-step Model}, journal = {CoRR}, volume = {abs/1905.13320}, year = {2019}, url = {http://arxiv.org/abs/1905.13320}, eprinttype = {arXiv}, eprint = {1905.13320}, timestamp = {Mon, 03 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1905-13320.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/AsadiML18, author = {Kavosh Asadi and Dipendra Misra and Michael L. Littman}, editor = {Jennifer G. Dy and Andreas Krause}, title = {Lipschitz Continuity in Model-based Reinforcement Learning}, booktitle = {Proceedings of the 35th International Conference on Machine Learning, {ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July 10-15, 2018}, series = {Proceedings of Machine Learning Research}, volume = {80}, pages = {264--273}, publisher = {{PMLR}}, year = {2018}, url = {http://proceedings.mlr.press/v80/asadi18a.html}, timestamp = {Wed, 03 Apr 2019 18:17:30 +0200}, biburl = {https://dblp.org/rec/conf/icml/AsadiML18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1804-07193, author = {Kavosh Asadi and Dipendra Misra and Michael L. Littman}, title = {Lipschitz Continuity in Model-based Reinforcement Learning}, journal = {CoRR}, volume = {abs/1804.07193}, year = {2018}, url = {http://arxiv.org/abs/1804.07193}, eprinttype = {arXiv}, eprint = {1804.07193}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1804-07193.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1806-01265, author = {Kavosh Asadi and Evan Cater and Dipendra Misra and Michael L. Littman}, title = {Equivalence Between Wasserstein and Value-Aware Model-based Reinforcement Learning}, journal = {CoRR}, volume = {abs/1806.01265}, year = {2018}, url = {http://arxiv.org/abs/1806.01265}, eprinttype = {arXiv}, eprint = {1806.01265}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1806-01265.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1811-00128, author = {Kavosh Asadi and Evan Cater and Dipendra Misra and Michael L. Littman}, title = {Towards a Simple Approach to Multi-step Model-based Reinforcement Learning}, journal = {CoRR}, volume = {abs/1811.00128}, year = {2018}, url = {http://arxiv.org/abs/1811.00128}, eprinttype = {arXiv}, eprint = {1811.00128}, timestamp = {Thu, 22 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1811-00128.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1812-01129, author = {Dilip Arumugam and David Abel and Kavosh Asadi and Nakul Gopalan and Christopher Grimm and Jun Ki Lee and Lucas Lehnert and Michael L. Littman}, title = {Mitigating Planner Overfitting in Model-Based Reinforcement Learning}, journal = {CoRR}, volume = {abs/1812.01129}, year = {2018}, url = {http://arxiv.org/abs/1812.01129}, eprinttype = {arXiv}, eprint = {1812.01129}, timestamp = {Tue, 01 Jan 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1812-01129.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/acl/WilliamsAZ17, author = {Jason D. Williams and Kavosh Asadi and Geoffrey Zweig}, editor = {Regina Barzilay and Min{-}Yen Kan}, title = {Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, {ACL} 2017, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers}, pages = {665--677}, publisher = {Association for Computational Linguistics}, year = {2017}, url = {https://doi.org/10.18653/v1/P17-1062}, doi = {10.18653/V1/P17-1062}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/acl/WilliamsAZ17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/AsadiL17, author = {Kavosh Asadi and Michael L. Littman}, editor = {Doina Precup and Yee Whye Teh}, title = {An Alternative Softmax Operator for Reinforcement Learning}, 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 = {243--252}, publisher = {{PMLR}}, year = {2017}, url = {http://proceedings.mlr.press/v70/asadi17a.html}, timestamp = {Wed, 29 May 2019 08:41:45 +0200}, biburl = {https://dblp.org/rec/conf/icml/AsadiL17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/WilliamsAZ17, author = {Jason D. Williams and Kavosh Asadi and Geoffrey Zweig}, title = {Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning}, journal = {CoRR}, volume = {abs/1702.03274}, year = {2017}, url = {http://arxiv.org/abs/1702.03274}, eprinttype = {arXiv}, eprint = {1702.03274}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/WilliamsAZ17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1709-00503, author = {Kavosh Asadi and Cameron Allen and Melrose Roderick and Abdel{-}rahman Mohamed and George Dimitri Konidaris and Michael L. Littman}, title = {Mean Actor Critic}, journal = {CoRR}, volume = {abs/1709.00503}, year = {2017}, url = {http://arxiv.org/abs/1709.00503}, eprinttype = {arXiv}, eprint = {1709.00503}, timestamp = {Tue, 19 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1709-00503.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/AsadiL16, author = {Kavosh Asadi and Michael L. Littman}, title = {A New Softmax Operator for Reinforcement Learning}, journal = {CoRR}, volume = {abs/1612.05628}, year = {2016}, url = {http://arxiv.org/abs/1612.05628}, eprinttype = {arXiv}, eprint = {1612.05628}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/AsadiL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/AsadiW16, author = {Kavosh Asadi and Jason D. Williams}, title = {Sample-efficient Deep Reinforcement Learning for Dialog Control}, journal = {CoRR}, volume = {abs/1612.06000}, year = {2016}, url = {http://arxiv.org/abs/1612.06000}, eprinttype = {arXiv}, eprint = {1612.06000}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/AsadiW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
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.