Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Amir-massoud Farahmand
@article{DBLP:journals/corr/abs-2403-05996, author = {Marcel Hussing and Claas Voelcker and Igor Gilitschenski and Amir{-}massoud Farahmand and Eric Eaton}, title = {Dissecting Deep {RL} with High Update Ratios: Combatting Value Overestimation and Divergence}, journal = {CoRR}, volume = {abs/2403.05996}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2403.05996}, doi = {10.48550/ARXIV.2403.05996}, eprinttype = {arXiv}, eprint = {2403.05996}, timestamp = {Thu, 04 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2403-05996.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/KastnerEF23, author = {Tyler Kastner and Murat A. Erdogdu and Amir{-}massoud Farahmand}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, title = {Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning}, 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/b0cd0e8027309ea050951e758b70d60e-Abstract-Conference.html}, timestamp = {Fri, 01 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/KastnerEF23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-17366, author = {Claas Voelcker and Arash Ahmadian and Romina Abachi and Igor Gilitschenski and Amir{-}massoud Farahmand}, title = {{\(\lambda\)}-AC: Learning latent decision-aware models for reinforcement learning in continuous state-spaces}, journal = {CoRR}, volume = {abs/2306.17366}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.17366}, doi = {10.48550/ARXIV.2306.17366}, eprinttype = {arXiv}, eprint = {2306.17366}, timestamp = {Mon, 03 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-17366.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2307-01708, author = {Tyler Kastner and Murat A. Erdogdu and Amir{-}massoud Farahmand}, title = {Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning}, journal = {CoRR}, volume = {abs/2307.01708}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2307.01708}, doi = {10.48550/ARXIV.2307.01708}, eprinttype = {arXiv}, eprint = {2307.01708}, timestamp = {Mon, 10 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2307-01708.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2307-08507, author = {Mete Kemertas and Allan D. Jepson and Amir{-}massoud Farahmand}, title = {Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients}, journal = {CoRR}, volume = {abs/2307.08507}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2307.08507}, doi = {10.48550/ARXIV.2307.08507}, eprinttype = {arXiv}, eprint = {2307.08507}, timestamp = {Tue, 25 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2307-08507.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2308-06703, author = {Avery Ma and Yangchen Pan and Amir{-}massoud Farahmand}, title = {Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods}, journal = {CoRR}, volume = {abs/2308.06703}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2308.06703}, doi = {10.48550/ARXIV.2308.06703}, eprinttype = {arXiv}, eprint = {2308.06703}, timestamp = {Wed, 23 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2308-06703.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-17855, author = {Amin Rakhsha and Mete Kemertas and Mohammad Ghavamzadeh and Amir{-}massoud Farahmand}, title = {Maximum Entropy Model Correction in Reinforcement Learning}, journal = {CoRR}, volume = {abs/2311.17855}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.17855}, doi = {10.48550/ARXIV.2311.17855}, eprinttype = {arXiv}, eprint = {2311.17855}, timestamp = {Tue, 05 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-17855.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-18495, author = {Avery Ma and Amir{-}massoud Farahmand and Yangchen Pan and Philip H. S. Torr and Jindong Gu}, title = {Improving Adversarial Transferability via Model Alignment}, journal = {CoRR}, volume = {abs/2311.18495}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.18495}, doi = {10.48550/ARXIV.2311.18495}, eprinttype = {arXiv}, eprint = {2311.18495}, timestamp = {Tue, 16 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-18495.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/LiuAFP22, author = {Guiliang Liu and Ashutosh Adhikari and Amir{-}massoud Farahmand and Pascal Poupart}, title = {Learning Object-Oriented Dynamics for Planning from Text}, booktitle = {The Tenth International Conference on Learning Representations, {ICLR} 2022, Virtual Event, April 25-29, 2022}, publisher = {OpenReview.net}, year = {2022}, url = {https://openreview.net/forum?id=B6EIcyp-Rb7}, timestamp = {Sat, 20 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iclr/LiuAFP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/VoelckerLGF22, author = {Claas Voelcker and Victor Liao and Animesh Garg and Amir{-}massoud Farahmand}, title = {Value Gradient weighted Model-Based Reinforcement Learning}, booktitle = {The Tenth International Conference on Learning Representations, {ICLR} 2022, Virtual Event, April 25-29, 2022}, publisher = {OpenReview.net}, year = {2022}, url = {https://openreview.net/forum?id=4-D6CZkRXxI}, timestamp = {Sat, 20 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iclr/VoelckerLGF22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/RakhshaWGF22, author = {Amin Rakhsha and Andrew Wang and Mohammad Ghavamzadeh and Amir{-}massoud Farahmand}, editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh}, title = {Operator Splitting Value Iteration}, 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/fa809df3ec53cc5781e5078b7d500a5d-Abstract-Conference.html}, timestamp = {Mon, 08 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/RakhshaWGF22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/uai/PanMFWYR022, author = {Yangchen Pan and Jincheng Mei and Amir{-}massoud Farahmand and Martha White and Hengshuai Yao and Mohsen Rohani and Jun Luo}, editor = {James Cussens and Kun Zhang}, title = {Understanding and mitigating the limitations of prioritized experience replay}, 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 = {1561--1571}, publisher = {{PMLR}}, year = {2022}, url = {https://proceedings.mlr.press/v180/pan22a.html}, timestamp = {Sat, 15 Oct 2022 12:08:13 +0200}, biburl = {https://dblp.org/rec/conf/uai/PanMFWYR022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2204-01464, author = {Claas Voelcker and Victor Liao and Animesh Garg and Amir{-}massoud Farahmand}, title = {Value Gradient weighted Model-Based Reinforcement Learning}, journal = {CoRR}, volume = {abs/2204.01464}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2204.01464}, doi = {10.48550/ARXIV.2204.01464}, eprinttype = {arXiv}, eprint = {2204.01464}, timestamp = {Wed, 06 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2204-01464.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-13937, author = {Amin Rakhsha and Andrew Wang and Mohammad Ghavamzadeh and Amir{-}massoud Farahmand}, title = {Operator Splitting Value Iteration}, journal = {CoRR}, volume = {abs/2211.13937}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.13937}, doi = {10.48550/ARXIV.2211.13937}, eprinttype = {arXiv}, eprint = {2211.13937}, timestamp = {Tue, 29 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-13937.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/FarahmandG21, author = {Amir Massoud Farahmand and Mohammad Ghavamzadeh}, editor = {Marina Meila and Tong Zhang}, title = {{PID} Accelerated Value Iteration Algorithm}, booktitle = {Proceedings of the 38th International Conference on Machine Learning, {ICML} 2021, 18-24 July 2021, Virtual Event}, series = {Proceedings of Machine Learning Research}, volume = {139}, pages = {3143--3153}, publisher = {{PMLR}}, year = {2021}, url = {http://proceedings.mlr.press/v139/farahmand21a.html}, timestamp = {Wed, 25 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icml/FarahmandG21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-11265, author = {Erfan Pirmorad and Faraz Khoshbakhtian and Farnam Mansouri and Amir{-}massoud Farahmand}, title = {Deep Reinforcement Learning for Online Control of Stochastic Partial Differential Equations}, journal = {CoRR}, volume = {abs/2110.11265}, year = {2021}, url = {https://arxiv.org/abs/2110.11265}, eprinttype = {arXiv}, eprint = {2110.11265}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-11265.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/PanMF20, author = {Yangchen Pan and Jincheng Mei and Amir{-}massoud Farahmand}, title = {Frequency-based Search-control in Dyna}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, year = {2020}, url = {https://openreview.net/forum?id=B1gskyStwr}, timestamp = {Thu, 07 May 2020 17:11:47 +0200}, biburl = {https://dblp.org/rec/conf/iclr/PanMF20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/PanIFW20, author = {Yangchen Pan and Ehsan Imani and Amir{-}massoud Farahmand and Martha White}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, title = {An implicit function learning approach for parametric modal regression}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, year = {2020}, url = {https://proceedings.neurips.cc/paper/2020/hash/83eaa6722798a773dd55e8fc7443aa09-Abstract.html}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/PanIFW20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-05822, author = {Yangchen Pan and Jincheng Mei and Amir{-}massoud Farahmand}, title = {Frequency-based Search-control in Dyna}, journal = {CoRR}, volume = {abs/2002.05822}, year = {2020}, url = {https://arxiv.org/abs/2002.05822}, eprinttype = {arXiv}, eprint = {2002.05822}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-05822.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-06195, author = {Yangchen Pan and Ehsan Imani and Martha White and Amir{-}massoud Farahmand}, title = {An implicit function learning approach for parametric modal regression}, journal = {CoRR}, volume = {abs/2002.06195}, year = {2020}, url = {https://arxiv.org/abs/2002.06195}, eprinttype = {arXiv}, eprint = {2002.06195}, timestamp = {Tue, 03 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-06195.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-00030, author = {Romina Abachi and Mohammad Ghavamzadeh and Amir{-}massoud Farahmand}, title = {Policy-Aware Model Learning for Policy Gradient Methods}, journal = {CoRR}, volume = {abs/2003.00030}, year = {2020}, url = {https://arxiv.org/abs/2003.00030}, eprinttype = {arXiv}, eprint = {2003.00030}, timestamp = {Tue, 10 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-00030.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2004-01832, author = {Avery Ma and Fartash Faghri and Amir{-}massoud Farahmand}, title = {Adversarial Robustness through Regularization: {A} Second-Order Approach}, journal = {CoRR}, volume = {abs/2004.01832}, year = {2020}, url = {https://arxiv.org/abs/2004.01832}, eprinttype = {arXiv}, eprint = {2004.01832}, timestamp = {Wed, 08 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2004-01832.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2007-09569, author = {Jincheng Mei and Yangchen Pan and Martha White and Amir{-}massoud Farahmand and Hengshuai Yao}, title = {Beyond Prioritized Replay: Sampling States in Model-Based {RL} via Simulated Priorities}, journal = {CoRR}, volume = {abs/2007.09569}, year = {2020}, url = {https://arxiv.org/abs/2007.09569}, eprinttype = {arXiv}, eprint = {2007.09569}, timestamp = {Tue, 28 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2007-09569.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-01753, author = {Rodrigo Toro Icarte and Richard Anthony Valenzano and Toryn Q. Klassen and Phillip J. K. Christoffersen and Amir{-}massoud Farahmand and Sheila A. McIlraith}, title = {The act of remembering: a study in partially observable reinforcement learning}, journal = {CoRR}, volume = {abs/2010.01753}, year = {2020}, url = {https://arxiv.org/abs/2010.01753}, eprinttype = {arXiv}, eprint = {2010.01753}, timestamp = {Tue, 10 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-01753.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/LawSFUZ19, author = {Marc T. Law and Jake Snell and Amir{-}massoud Farahmand and Raquel Urtasun and Richard S. Zemel}, title = {Dimensionality Reduction for Representing the Knowledge of Probabilistic Models}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, year = {2019}, url = {https://openreview.net/forum?id=SygD-hCcF7}, timestamp = {Thu, 25 Jul 2019 13:03:15 +0200}, biburl = {https://dblp.org/rec/conf/iclr/LawSFUZ19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcai/PanYFW19, author = {Yangchen Pan and Hengshuai Yao and Amir{-}massoud Farahmand and Martha White}, editor = {Sarit Kraus}, title = {Hill Climbing on Value Estimates for Search-control in Dyna}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, pages = {3209--3215}, publisher = {ijcai.org}, year = {2019}, url = {https://doi.org/10.24963/ijcai.2019/445}, doi = {10.24963/IJCAI.2019/445}, timestamp = {Tue, 20 Aug 2019 16:18:18 +0200}, biburl = {https://dblp.org/rec/conf/ijcai/PanYFW19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/miccai/AkroutFJA19, author = {Mohamed Akrout and Amir{-}massoud Farahmand and Tory Jarmain and Latif Abid}, editor = {Dinggang Shen and Tianming Liu and Terry M. Peters and Lawrence H. Staib and Caroline Essert and Sean Zhou and Pew{-}Thian Yap and Ali R. Khan}, title = {Improving Skin Condition Classification with a Visual Symptom Checker Trained Using Reinforcement Learning}, booktitle = {Medical Image Computing and Computer Assisted Intervention - {MICCAI} 2019 - 22nd International Conference, Shenzhen, China, October 13-17, 2019, Proceedings, Part {IV}}, series = {Lecture Notes in Computer Science}, volume = {11767}, pages = {549--557}, publisher = {Springer}, year = {2019}, url = {https://doi.org/10.1007/978-3-030-32251-9\_60}, doi = {10.1007/978-3-030-32251-9\_60}, timestamp = {Mon, 19 Feb 2024 14:24:13 +0100}, biburl = {https://dblp.org/rec/conf/miccai/AkroutFJA19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/Farahmand19, author = {Amir{-}massoud Farahmand}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, title = {Value Function in Frequency Domain and the Characteristic Value Iteration Algorithm}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, pages = {14780--14790}, year = {2019}, url = {https://proceedings.neurips.cc/paper/2019/hash/4e38d30e656da5ae9d3a425109ce9e04-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/Farahmand19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1903-03495, author = {Mohamed Akrout and Amir{-}massoud Farahmand and Tory Jarmain and Latif Abid}, title = {Improving Skin Condition Classification with a Visual Symptom Checker Trained using Reinforcement Learning}, journal = {CoRR}, volume = {abs/1903.03495}, year = {2019}, url = {http://arxiv.org/abs/1903.03495}, eprinttype = {arXiv}, eprint = {1903.03495}, timestamp = {Tue, 02 Apr 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1903-03495.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1906-07791, author = {Yangchen Pan and Hengshuai Yao and Amir{-}massoud Farahmand and Martha White}, title = {Hill Climbing on Value Estimates for Search-control in Dyna}, journal = {CoRR}, volume = {abs/1906.07791}, year = {2019}, url = {http://arxiv.org/abs/1906.07791}, eprinttype = {arXiv}, eprint = {1906.07791}, timestamp = {Mon, 24 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1906-07791.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/PanFWNGN18, author = {Yangchen Pan and Amir{-}massoud Farahmand and Martha White and Saleh Nabi and Piyush Grover and Daniel Nikovski}, editor = {Jennifer G. Dy and Andreas Krause}, title = {Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control}, 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 = {3983--3992}, publisher = {{PMLR}}, year = {2018}, url = {http://proceedings.mlr.press/v80/pan18a.html}, timestamp = {Wed, 03 Apr 2019 18:17:30 +0200}, biburl = {https://dblp.org/rec/conf/icml/PanFWNGN18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/Farahmand18, author = {Amir{-}massoud Farahmand}, editor = {Samy Bengio and Hanna M. Wallach and Hugo Larochelle and Kristen Grauman and Nicol{\`{o}} Cesa{-}Bianchi and Roman Garnett}, title = {Iterative Value-Aware Model Learning}, booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr{\'{e}}al, Canada}, pages = {9090--9101}, year = {2018}, url = {https://proceedings.neurips.cc/paper/2018/hash/7a2347d96752880e3d58d72e9813cc14-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/Farahmand18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1806-06931, author = {Yangchen Pan and Amir{-}massoud Farahmand and Martha White and Saleh Nabi and Piyush Grover and Daniel Nikovski}, title = {Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control}, journal = {CoRR}, volume = {abs/1806.06931}, year = {2018}, url = {http://arxiv.org/abs/1806.06931}, eprinttype = {arXiv}, eprint = {1806.06931}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1806-06931.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1811-06165, author = {Mohamed Akrout and Amir{-}massoud Farahmand and Tory Jarmain}, title = {Improving Skin Condition Classification with a Question Answering Model}, journal = {CoRR}, volume = {abs/1811.06165}, year = {2018}, url = {http://arxiv.org/abs/1811.06165}, eprinttype = {arXiv}, eprint = {1811.06165}, timestamp = {Sun, 25 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1811-06165.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/FarahmandBN17, author = {Amir Massoud Farahmand and Andr{\'{e}} Barreto and Daniel Nikovski}, editor = {Aarti Singh and Xiaojin (Jerry) Zhu}, title = {Value-Aware Loss Function for Model-based Reinforcement Learning}, booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, {AISTATS} 2017, 20-22 April 2017, Fort Lauderdale, FL, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {54}, pages = {1486--1494}, publisher = {{PMLR}}, year = {2017}, url = {http://proceedings.mlr.press/v54/farahmand17a.html}, timestamp = {Mon, 10 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/aistats/FarahmandBN17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/amcc/FarahmandNN17, author = {Amir{-}massoud Farahmand and Saleh Nabi and Daniel Nikolaev Nikovski}, title = {Deep reinforcement learning for partial differential equation control}, booktitle = {2017 American Control Conference, {ACC} 2017, Seattle, WA, USA, May 24-26, 2017}, pages = {3120--3127}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.23919/ACC.2017.7963427}, doi = {10.23919/ACC.2017.7963427}, timestamp = {Fri, 03 Dec 2021 13:04:31 +0100}, biburl = {https://dblp.org/rec/conf/amcc/FarahmandNN17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/FarahmandPN17, author = {Amir{-}massoud Farahmand and Sepideh Pourazarm and Daniel Nikovski}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, title = {Random Projection Filter Bank for Time Series Data}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, pages = {6562--6572}, year = {2017}, url = {https://proceedings.neurips.cc/paper/2017/hash/ca3ec598002d2e7662e2ef4bdd58278b-Abstract.html}, timestamp = {Thu, 21 Jan 2021 13:58:27 +0100}, biburl = {https://dblp.org/rec/conf/nips/FarahmandPN17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ssci/JhaNYF17, author = {Devesh K. Jha and Daniel Nikovski and William Yerazunis and Amir{-}massoud Farahmand}, title = {Learning to regulate rolling ball motion}, booktitle = {2017 {IEEE} Symposium Series on Computational Intelligence, {SSCI} 2017, Honolulu, HI, USA, November 27 - Dec. 1, 2017}, pages = {1--6}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/SSCI.2017.8285376}, doi = {10.1109/SSCI.2017.8285376}, timestamp = {Wed, 16 Oct 2019 14:14:56 +0200}, biburl = {https://dblp.org/rec/conf/ssci/JhaNYF17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/Hara0TF17, author = {Kota Hara and Ming{-}Yu Liu and Oncel Tuzel and Amir{-}massoud Farahmand}, title = {Attentional Network for Visual Object Detection}, journal = {CoRR}, volume = {abs/1702.01478}, year = {2017}, url = {http://arxiv.org/abs/1702.01478}, eprinttype = {arXiv}, eprint = {1702.01478}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/Hara0TF17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/FarahmandGSM16, author = {Amir{-}massoud Farahmand and Mohammad Ghavamzadeh and Csaba Szepesv{\'{a}}ri and Shie Mannor}, title = {Regularized Policy Iteration with Nonparametric Function Spaces}, journal = {J. Mach. Learn. Res.}, volume = {17}, pages = {139:1--139:66}, year = {2016}, url = {http://jmlr.org/papers/v17/13-016.html}, timestamp = {Wed, 10 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/FarahmandGSM16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/FarahmandNIK16, author = {Amir{-}massoud Farahmand and Daniel Nikolaev Nikovski and Yuji Igarashi and Hiroki Konaka}, editor = {Dale Schuurmans and Michael P. Wellman}, title = {Truncated Approximate Dynamic Programming with Task-Dependent Terminal Value}, booktitle = {Proceedings of the Thirtieth {AAAI} Conference on Artificial Intelligence, February 12-17, 2016, Phoenix, Arizona, {USA}}, pages = {3123--3129}, publisher = {{AAAI} Press}, year = {2016}, url = {https://doi.org/10.1609/aaai.v30i1.10397}, doi = {10.1609/AAAI.V30I1.10397}, timestamp = {Mon, 04 Sep 2023 15:08:28 +0200}, biburl = {https://dblp.org/rec/conf/aaai/FarahmandNIK16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/amcc/BenosmanFX16, author = {Mouhacine Benosman and Amir{-}massoud Farahmand and Meng Xia}, title = {Learning-based modular indirect adaptive control for a class of nonlinear systems}, booktitle = {2016 American Control Conference, {ACC} 2016, Boston, MA, USA, July 6-8, 2016}, pages = {733--738}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ACC.2016.7525001}, doi = {10.1109/ACC.2016.7525001}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/amcc/BenosmanFX16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cdc/FarahmandNGN16, author = {Amir{-}massoud Farahmand and Saleh Nabi and Piyush Grover and Daniel Nikovski}, title = {Learning to control partial differential equations: Regularized Fitted Q-Iteration approach}, booktitle = {55th {IEEE} Conference on Decision and Control, {CDC} 2016, Las Vegas, NV, USA, December 12-14, 2016}, pages = {4578--4585}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/CDC.2016.7798966}, doi = {10.1109/CDC.2016.7798966}, timestamp = {Fri, 04 Mar 2022 13:29:43 +0100}, biburl = {https://dblp.org/rec/conf/cdc/FarahmandNGN16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/aim/AlbrechtBBBCDEF15, author = {Stefano V. Albrecht and Andr{\'{e}} da Motta Salles Barreto and Darius Braziunas and David L. Buckeridge and Heriberto Cuay{\'{a}}huitl and Nina Dethlefs and Markus Endres and Amir{-}massoud Farahmand and Mark Fox and Lutz Frommberger and Sam Ganzfried and Yolanda Gil and S{\'{e}}bastien Guillet and Lawrence E. Hunter and Arnav Jhala and Kristian Kersting and George Dimitri Konidaris and Freddy L{\'{e}}cu{\'{e}} and Sheila A. McIlraith and Sriraam Natarajan and Zeinab Noorian and David Poole and R{\'{e}}mi Ronfard and Alessandro Saffiotti and Arash Shaban{-}Nejad and Biplav Srivastava and Gerald Tesauro and Rosario Uceda{-}Sosa and Guy Van den Broeck and Martijn van Otterlo and Byron C. Wallace and Paul Weng and Jenna Wiens and Jie Zhang}, title = {Reports of the {AAAI} 2014 Conference Workshops}, journal = {{AI} Mag.}, volume = {36}, number = {1}, pages = {87--98}, year = {2015}, url = {https://doi.org/10.1609/aimag.v36i1.2575}, doi = {10.1609/AIMAG.V36I1.2575}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/aim/AlbrechtBBBCDEF15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tac/FarahmandPBG15, author = {Amir{-}massoud Farahmand and Doina Precup and Andr{\'{e}} da Motta Salles Barreto and Mohammad Ghavamzadeh}, title = {Classification-Based Approximate Policy Iteration}, journal = {{IEEE} Trans. Autom. Control.}, volume = {60}, number = {11}, pages = {2989--2993}, year = {2015}, url = {https://doi.org/10.1109/TAC.2015.2418411}, doi = {10.1109/TAC.2015.2418411}, timestamp = {Wed, 20 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tac/FarahmandPBG15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/HuangFKB15, author = {De{-}An Huang and Amir{-}massoud Farahmand and Kris M. Kitani and James Andrew Bagnell}, editor = {Blai Bonet and Sven Koenig}, title = {Approximate MaxEnt Inverse Optimal Control and Its Application for Mental Simulation of Human Interactions}, booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence, January 25-30, 2015, Austin, Texas, {USA}}, pages = {2673--2679}, publisher = {{AAAI} Press}, year = {2015}, url = {https://doi.org/10.1609/aaai.v29i1.9605}, doi = {10.1609/AAAI.V29I1.9605}, timestamp = {Mon, 18 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aaai/HuangFKB15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/BenosmanFX15, author = {Mouhacine Benosman and Amir{-}massoud Farahmand and Meng Xia}, title = {Learning-Based Modular Indirect Adaptive Control for a Class of Nonlinear Systems}, journal = {CoRR}, volume = {abs/1509.07860}, year = {2015}, url = {http://arxiv.org/abs/1509.07860}, eprinttype = {arXiv}, eprint = {1509.07860}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/BenosmanFX15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/BachmanFP14, author = {Philip Bachman and Amir{-}massoud Farahmand and Doina Precup}, title = {Sample-based approximate regularization}, 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 = {1926--1934}, publisher = {JMLR.org}, year = {2014}, url = {http://proceedings.mlr.press/v32/bachman14.html}, timestamp = {Wed, 29 May 2019 08:41:45 +0200}, biburl = {https://dblp.org/rec/conf/icml/BachmanFP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/FarahmandPBG14, author = {Amir{-}massoud Farahmand and Doina Precup and Andr{\'{e}} da Motta Salles Barreto and Mohammad Ghavamzadeh}, title = {Classification-based Approximate Policy Iteration: Experiments and Extended Discussions}, journal = {CoRR}, volume = {abs/1407.0449}, year = {2014}, url = {http://arxiv.org/abs/1407.0449}, eprinttype = {arXiv}, eprint = {1407.0449}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/FarahmandPBG14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/KimFPP13, author = {Beomjoon Kim and Amir{-}massoud Farahmand and Joelle Pineau and Doina Precup}, editor = {Christopher J. C. Burges and L{\'{e}}on Bottou and Zoubin Ghahramani and Kilian Q. Weinberger}, title = {Learning from Limited Demonstrations}, booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States}, pages = {2859--2867}, year = {2013}, url = {https://proceedings.neurips.cc/paper/2013/hash/fd5c905bcd8c3348ad1b35d7231ee2b1-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/KimFPP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/FardGFPP13, author = {Mahdi Milani Fard and Yuri Grinberg and Amir{-}massoud Farahmand and Joelle Pineau and Doina Precup}, editor = {Christopher J. C. Burges and L{\'{e}}on Bottou and Zoubin Ghahramani and Kilian Q. Weinberger}, title = {Bellman Error Based Feature Generation using Random Projections on Sparse Spaces}, booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States}, pages = {3030--3038}, year = {2013}, url = {https://proceedings.neurips.cc/paper/2013/hash/86e8f7ab32cfd12577bc2619bc635690-Abstract.html}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/FardGFPP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/FarahmandP12, author = {Amir Massoud Farahmand and Doina Precup}, editor = {Peter L. Bartlett and Fernando C. N. Pereira and Christopher J. C. Burges and L{\'{e}}on Bottou and Kilian Q. Weinberger}, title = {Value Pursuit Iteration}, booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States}, pages = {1349--1357}, year = {2012}, url = {https://proceedings.neurips.cc/paper/2012/hash/ab233b682ec355648e7891e66c54191b-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/FarahmandP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1207-5554, author = {Mahdi Milani Fard and Yuri Grinberg and Amir Massoud Farahmand and Joelle Pineau and Doina Precup}, title = {Bellman Error Based Feature Generation using Random Projections on Sparse Spaces}, journal = {CoRR}, volume = {abs/1207.5554}, year = {2012}, url = {http://arxiv.org/abs/1207.5554}, eprinttype = {arXiv}, eprint = {1207.5554}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1207-5554.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ml/FarahmandS11, author = {Amir Massoud Farahmand and Csaba Szepesv{\'{a}}ri}, title = {Model selection in reinforcement learning}, journal = {Mach. Learn.}, volume = {85}, number = {3}, pages = {299--332}, year = {2011}, url = {https://doi.org/10.1007/s10994-011-5254-7}, doi = {10.1007/S10994-011-5254-7}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ml/FarahmandS11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/Farahmand11, author = {Amir Massoud Farahmand}, editor = {John Shawe{-}Taylor and Richard S. Zemel and Peter L. Bartlett and Fernando C. N. Pereira and Kilian Q. Weinberger}, title = {Action-Gap Phenomenon in Reinforcement Learning}, booktitle = {Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, Granada, Spain}, pages = {172--180}, year = {2011}, url = {https://proceedings.neurips.cc/paper/2011/hash/013d407166ec4fa56eb1e1f8cbe183b9-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/Farahmand11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tec/FarahmandALA10, author = {Amir Massoud Farahmand and Majid Nili Ahmadabadi and Caro Lucas and Babak Nadjar Araabi}, title = {Interaction of Culture-Based Learning and Cooperative Co-Evolution and its Application to Automatic Behavior-Based System Design}, journal = {{IEEE} Trans. Evol. Comput.}, volume = {14}, number = {1}, pages = {23--57}, year = {2010}, url = {https://doi.org/10.1109/TEVC.2009.2016216}, doi = {10.1109/TEVC.2009.2016216}, timestamp = {Mon, 26 Oct 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tec/FarahmandALA10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/ShademanFJ10, author = {Azad Shademan and Amir Massoud Farahmand and Martin J{\"{a}}gersand}, title = {Robust Jacobian estimation for uncalibrated visual servoing}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2010, Anchorage, Alaska, USA, 3-7 May 2010}, pages = {5564--5569}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/ROBOT.2010.5509911}, doi = {10.1109/ROBOT.2010.5509911}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/ShademanFJ10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/FarahmandMS10, author = {Amir Massoud Farahmand and R{\'{e}}mi Munos and Csaba Szepesv{\'{a}}ri}, editor = {John D. Lafferty and Christopher K. I. Williams and John Shawe{-}Taylor and Richard S. Zemel and Aron Culotta}, title = {Error Propagation for Approximate Policy and Value Iteration}, booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, Vancouver, British Columbia, Canada}, pages = {568--576}, publisher = {Curran Associates, Inc.}, year = {2010}, url = {https://proceedings.neurips.cc/paper/2010/hash/65cc2c8205a05d7379fa3a6386f710e1-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/FarahmandMS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/amcc/FarahmandGSM09, author = {Amir Massoud Farahmand and Mohammad Ghavamzadeh and Csaba Szepesv{\'{a}}ri and Shie Mannor}, title = {Regularized Fitted Q-Iteration for planning in continuous-space Markovian decision problems}, booktitle = {American Control Conference, {ACC} 2009. St. Louis, Missouri, USA, June 10-12, 2009}, pages = {725--730}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ACC.2009.5160611}, doi = {10.1109/ACC.2009.5160611}, timestamp = {Fri, 03 Dec 2021 13:02:58 +0100}, biburl = {https://dblp.org/rec/conf/amcc/FarahmandGSM09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/crv/ShademanFJ09, author = {Azad Shademan and Amir Massoud Farahmand and Martin J{\"{a}}gersand}, title = {Towards Learning Robotic Reaching and Pointing: An Uncalibrated Visual Servoing Approach}, booktitle = {Sixth Canadian Conference on Computer and Robot Vision, {CRV} 2009, Kelowna, British Columbia, Canada, May 25-27, 2009}, pages = {229--236}, publisher = {{IEEE} Computer Society}, year = {2009}, url = {https://doi.org/10.1109/CRV.2009.47}, doi = {10.1109/CRV.2009.47}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/crv/ShademanFJ09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/FarahmandSJS09, author = {Amir Massoud Farahmand and Azad Shademan and Martin J{\"{a}}gersand and Csaba Szepesv{\'{a}}ri}, title = {Model-based and model-free reinforcement learning for visual servoing}, booktitle = {2009 {IEEE} International Conference on Robotics and Automation, {ICRA} 2009, Kobe, Japan, May 12-17, 2009}, pages = {2917--2924}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ROBOT.2009.5152834}, doi = {10.1109/ROBOT.2009.5152834}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/FarahmandSJS09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ewrl/FarahmandGSM08, author = {Amir Massoud Farahmand and Mohammad Ghavamzadeh and Csaba Szepesv{\'{a}}ri and Shie Mannor}, editor = {Sertan Girgin and Manuel Loth and R{\'{e}}mi Munos and Philippe Preux and Daniil Ryabko}, title = {Regularized Fitted Q-Iteration: Application to Planning}, booktitle = {Recent Advances in Reinforcement Learning, 8th European Workshop, {EWRL} 2008, Villeneuve d'Ascq, France, June 30 - July 3, 2008, Revised and Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {5323}, pages = {55--68}, publisher = {Springer}, year = {2008}, url = {https://doi.org/10.1007/978-3-540-89722-4\_5}, doi = {10.1007/978-3-540-89722-4\_5}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ewrl/FarahmandGSM08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/FarahmandGSM08, author = {Amir Massoud Farahmand and Mohammad Ghavamzadeh and Csaba Szepesv{\'{a}}ri and Shie Mannor}, editor = {Daphne Koller and Dale Schuurmans and Yoshua Bengio and L{\'{e}}on Bottou}, title = {Regularized Policy Iteration}, booktitle = {Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008}, pages = {441--448}, publisher = {Curran Associates, Inc.}, year = {2008}, url = {https://proceedings.neurips.cc/paper/2008/hash/aeb3135b436aa55373822c010763dd54-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/FarahmandGSM08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/FarahmandSA07, author = {Amir Massoud Farahmand and Csaba Szepesv{\'{a}}ri and Jean{-}Yves Audibert}, editor = {Zoubin Ghahramani}, title = {Manifold-adaptive dimension estimation}, 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 = {265--272}, publisher = {{ACM}}, year = {2007}, url = {https://doi.org/10.1145/1273496.1273530}, doi = {10.1145/1273496.1273530}, timestamp = {Tue, 06 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icml/FarahmandSA07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/FarahmandSJ07, author = {Amir Massoud Farahmand and Azad Shademan and Martin J{\"{a}}gersand}, title = {Global visual-motor estimation for uncalibrated visual servoing}, booktitle = {2007 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, October 29 - November 2, 2007, Sheraton Hotel and Marina, San Diego, California, {USA}}, pages = {1969--1974}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/IROS.2007.4399506}, doi = {10.1109/IROS.2007.4399506}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/FarahmandSJ07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cec/FarahmandALA06, author = {Amir Massoud Farahmand and Majid Nili Ahmadabadi and Caro Lucas and Babak Nadjar Araabi}, title = {Hybrid Behavior Co-evolution and Structure Learning in Behavior-based Systems}, booktitle = {{IEEE} International Conference on Evolutionary Computation, {CEC} 2006, part of {WCCI} 2006, Vancouver, BC, Canada, 16-21 July 2006}, pages = {275--282}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/CEC.2006.1688319}, doi = {10.1109/CEC.2006.1688319}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/cec/FarahmandALA06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/AzarAFA06, author = {Mohammad G. Azar and Majid Nili Ahmadabadi and Amir Massoud Farahmand and Babak Nadjar Araabi}, title = {Learning to Coordinate Behaviors in Soft Behavior-Based Systems Using Reinforcement Learning}, booktitle = {Proceedings of the International Joint Conference on Neural Networks, {IJCNN} 2006, part of the {IEEE} World Congress on Computational Intelligence, {WCCI} 2006, Vancouver, BC, Canada, 16-21 July 2006}, pages = {241--248}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/IJCNN.2006.246687}, doi = {10.1109/IJCNN.2006.246687}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/AzarAFA06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/FarahmandY06, author = {Amir Massoud Farahmand and Mohammad Javad Yazdanpanah}, title = {Channel Assignment using Chaotic Simulated Annealing Enhanced Hopfield Neural Network}, booktitle = {Proceedings of the International Joint Conference on Neural Networks, {IJCNN} 2006, part of the {IEEE} World Congress on Computational Intelligence, {WCCI} 2006, Vancouver, BC, Canada, 16-21 July 2006}, pages = {4491--4497}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/IJCNN.2006.247073}, doi = {10.1109/IJCNN.2006.247073}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/FarahmandY06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cdc/FarahmandY05, author = {Amir Massoud Farahmand and Mohammad Javad Yazdanpanah}, title = {Locally Optimal Takagi-Sugeno Fuzzy Controllers}, booktitle = {44th {IEEE} {IEEE} Conference on Decision and Control and 8th European Control Conference Control, {CDC/ECC} 2005, Seville, Spain, 12-15 December, 2005}, pages = {4095--4099}, publisher = {{IEEE}}, year = {2005}, url = {https://doi.org/10.1109/CDC.2005.1582803}, doi = {10.1109/CDC.2005.1582803}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cdc/FarahmandY05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/FarahmandAA04, author = {Amir Massoud Farahmand and Majid Nili Ahmadabadi and Babak Nadjar Araabi}, title = {Behavior hierarchy learning in a behavior-based system using reinforcement learning}, booktitle = {2004 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, Sendai, Japan, September 28 - October 2, 2004}, pages = {2050--2055}, publisher = {{IEEE}}, year = {2004}, url = {https://doi.org/10.1109/IROS.2004.1389699}, doi = {10.1109/IROS.2004.1389699}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/FarahmandAA04.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.