Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Eiji Uchibe
@article{DBLP:journals/ijon/AslU23, author = {Hamed Jabbari Asl and Eiji Uchibe}, title = {Online Reinforcement Learning Control of Nonlinear Dynamic Systems: {A} State-action Value Function Based Solution}, journal = {Neurocomputing}, volume = {544}, pages = {126291}, year = {2023}, url = {https://doi.org/10.1016/j.neucom.2023.126291}, doi = {10.1016/J.NEUCOM.2023.126291}, timestamp = {Sun, 04 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijon/AslU23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/MatsuoLSPSSUM22, author = {Yutaka Matsuo and Yann LeCun and Maneesh Sahani and Doina Precup and David Silver and Masashi Sugiyama and Eiji Uchibe and Jun Morimoto}, title = {Deep learning, reinforcement learning, and world models}, journal = {Neural Networks}, volume = {152}, pages = {267--275}, year = {2022}, url = {https://doi.org/10.1016/j.neunet.2022.03.037}, doi = {10.1016/J.NEUNET.2022.03.037}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/nn/MatsuoLSPSSUM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/YamanokuchiKTUM22, author = {Tomoya Yamanokuchi and Yuhwan Kwon and Yoshihisa Tsurumine and Eiji Uchibe and Jun Morimoto and Takamitsu Matsubara}, title = {Randomized-to-Canonical Model Predictive Control for Real-World Visual Robotic Manipulation}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {7}, number = {4}, pages = {8964--8971}, year = {2022}, url = {https://doi.org/10.1109/LRA.2022.3189156}, doi = {10.1109/LRA.2022.3189156}, timestamp = {Mon, 05 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ral/YamanokuchiKTUM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/Uchibe22, author = {Eiji Uchibe}, title = {Model-Based Imitation Learning Using Entropy Regularization of Model and Policy}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {7}, number = {4}, pages = {10922--10929}, year = {2022}, url = {https://doi.org/10.1109/LRA.2022.3196139}, doi = {10.1109/LRA.2022.3196139}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/Uchibe22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ssci/AslU22, author = {Hamed Jabbari Asl and Eiji Uchibe}, editor = {Hisao Ishibuchi and Chee{-}Keong Kwoh and Ah{-}Hwee Tan and Dipti Srinivasan and Chunyan Miao and Anupam Trivedi and Keeley A. Crockett}, title = {Online Data-Driven Inverse Reinforcement Learning for Deterministic Systems}, booktitle = {{IEEE} Symposium Series on Computational Intelligence, {SSCI} 2022, Singapore, December 4-7, 2022}, pages = {884--889}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/SSCI51031.2022.10022226}, doi = {10.1109/SSCI51031.2022.10022226}, timestamp = {Wed, 08 Feb 2023 22:09:16 +0100}, biburl = {https://dblp.org/rec/conf/ssci/AslU22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-07467, author = {Lingwei Zhu and Zheng Chen and Eiji Uchibe and Takamitsu Matsubara}, title = {q-Munchausen Reinforcement Learning}, journal = {CoRR}, volume = {abs/2205.07467}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.07467}, doi = {10.48550/ARXIV.2205.07467}, eprinttype = {arXiv}, eprint = {2205.07467}, timestamp = {Wed, 18 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-07467.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-07885, author = {Lingwei Zhu and Zheng Chen and Eiji Uchibe and Takamitsu Matsubara}, title = {Enforcing {KL} Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning}, journal = {CoRR}, volume = {abs/2205.07885}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.07885}, doi = {10.48550/ARXIV.2205.07885}, eprinttype = {arXiv}, eprint = {2205.07885}, timestamp = {Tue, 24 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-07885.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-10101, author = {Eiji Uchibe}, title = {Model-Based Imitation Learning Using Entropy Regularization of Model and Policy}, journal = {CoRR}, volume = {abs/2206.10101}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.10101}, doi = {10.48550/ARXIV.2206.10101}, eprinttype = {arXiv}, eprint = {2206.10101}, timestamp = {Mon, 27 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-10101.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2207-01840, author = {Tomoya Yamanokuchi and Yuhwan Kwon and Yoshihisa Tsurumine and Eiji Uchibe and Jun Morimoto and Takamitsu Matsubara}, title = {Randomized-to-Canonical Model Predictive Control for Real-world Visual Robotic Manipulation}, journal = {CoRR}, volume = {abs/2207.01840}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2207.01840}, doi = {10.48550/ARXIV.2207.01840}, eprinttype = {arXiv}, eprint = {2207.01840}, timestamp = {Wed, 06 Jul 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2207-01840.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/WangEU21, author = {Jiexin Wang and Stefan Elfwing and Eiji Uchibe}, title = {Modular deep reinforcement learning from reward and punishment for robot navigation}, journal = {Neural Networks}, volume = {135}, pages = {115--126}, year = {2021}, url = {https://doi.org/10.1016/j.neunet.2020.12.001}, doi = {10.1016/J.NEUNET.2020.12.001}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/WangEU21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/UchibeD21, author = {Eiji Uchibe and Kenji Doya}, title = {Forward and inverse reinforcement learning sharing network weights and hyperparameters}, journal = {Neural Networks}, volume = {144}, pages = {138--153}, year = {2021}, url = {https://doi.org/10.1016/j.neunet.2021.08.017}, doi = {10.1016/J.NEUNET.2021.08.017}, timestamp = {Fri, 13 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/nn/UchibeD21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/MacphersonMGMUH21, author = {Tom Macpherson and Masayuki Matsumoto and Hiroaki Gomi and Jun Morimoto and Eiji Uchibe and Takatoshi Hikida}, title = {Parallel and hierarchical neural mechanisms for adaptive and predictive behavioral control}, journal = {Neural Networks}, volume = {144}, pages = {507--521}, year = {2021}, url = {https://doi.org/10.1016/j.neunet.2021.09.009}, doi = {10.1016/J.NEUNET.2021.09.009}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/MacphersonMGMUH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2008-07284, author = {Eiji Uchibe and Kenji Doya}, title = {Imitation learning based on entropy-regularized forward and inverse reinforcement learning}, journal = {CoRR}, volume = {abs/2008.07284}, year = {2020}, url = {https://arxiv.org/abs/2008.07284}, eprinttype = {arXiv}, eprint = {2008.07284}, timestamp = {Fri, 21 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2008-07284.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/finr/OhnishiUYNYI19, author = {Shota Ohnishi and Eiji Uchibe and Yotaro Yamaguchi and Kosuke Nakanishi and Yuji Yasui and Shin Ishii}, title = {Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning}, journal = {Frontiers Neurorobotics}, volume = {13}, pages = {103}, year = {2019}, url = {https://doi.org/10.3389/fnbot.2019.00103}, doi = {10.3389/FNBOT.2019.00103}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/finr/OhnishiUYNYI19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ras/TsurumineCUM19, author = {Yoshihisa Tsurumine and Yunduan Cui and Eiji Uchibe and Takamitsu Matsubara}, title = {Deep reinforcement learning with smooth policy update: Application to robotic cloth manipulation}, journal = {Robotics Auton. Syst.}, volume = {112}, pages = {72--83}, year = {2019}, url = {https://doi.org/10.1016/j.robot.2018.11.004}, doi = {10.1016/J.ROBOT.2018.11.004}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ras/TsurumineCUM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/KozunoUD19, author = {Tadashi Kozuno and Eiji Uchibe and Kenji Doya}, editor = {Kamalika Chaudhuri and Masashi Sugiyama}, title = {Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement Learning}, booktitle = {The 22nd International Conference on Artificial Intelligence and Statistics, {AISTATS} 2019, 16-18 April 2019, Naha, Okinawa, Japan}, series = {Proceedings of Machine Learning Research}, volume = {89}, pages = {2995--3003}, publisher = {{PMLR}}, year = {2019}, url = {http://proceedings.mlr.press/v89/kozuno19a.html}, timestamp = {Fri, 07 Jun 2019 09:03:47 +0200}, biburl = {https://dblp.org/rec/conf/aistats/KozunoUD19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/alr/KinjoUD18, author = {Ken Kinjo and Eiji Uchibe and Kenji Doya}, title = {Robustness of linearly solvable Markov games employing inaccurate dynamics model}, journal = {Artif. Life Robotics}, volume = {23}, number = {1}, pages = {1--9}, year = {2018}, url = {https://doi.org/10.1007/s10015-017-0401-2}, doi = {10.1007/S10015-017-0401-2}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/alr/KinjoUD18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/finr/Uchibe18, author = {Eiji Uchibe}, title = {Cooperative and Competitive Reinforcement and Imitation Learning for a Mixture of Heterogeneous Learning Modules}, journal = {Frontiers Neurorobotics}, volume = {12}, pages = {61}, year = {2018}, url = {https://doi.org/10.3389/fnbot.2018.00061}, doi = {10.3389/FNBOT.2018.00061}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/finr/Uchibe18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/ElfwingUD18, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, title = {Sigmoid-weighted linear units for neural network function approximation in reinforcement learning}, journal = {Neural Networks}, volume = {107}, pages = {3--11}, year = {2018}, url = {https://doi.org/10.1016/j.neunet.2017.12.012}, doi = {10.1016/J.NEUNET.2017.12.012}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/ElfwingUD18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/npl/Uchibe18, author = {Eiji Uchibe}, title = {Model-Free Deep Inverse Reinforcement Learning by Logistic Regression}, journal = {Neural Process. Lett.}, volume = {47}, number = {3}, pages = {891--905}, year = {2018}, url = {https://doi.org/10.1007/s11063-017-9702-7}, doi = {10.1007/S11063-017-9702-7}, timestamp = {Thu, 09 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/npl/Uchibe18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/gecco/ElfwingUD18, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, editor = {Hern{\'{a}}n E. Aguirre and Keiki Takadama}, title = {Online meta-learning by parallel algorithm competition}, booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference, {GECCO} 2018, Kyoto, Japan, July 15-19, 2018}, pages = {426--433}, publisher = {{ACM}}, year = {2018}, url = {https://doi.org/10.1145/3205455.3205486}, doi = {10.1145/3205455.3205486}, timestamp = {Wed, 21 Nov 2018 12:43:54 +0100}, biburl = {https://dblp.org/rec/conf/gecco/ElfwingUD18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/gecco/Uchibe18, author = {Eiji Uchibe}, editor = {Hern{\'{a}}n E. Aguirre and Keiki Takadama}, title = {Efficient sample reuse in policy search by multiple importance sampling}, booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference, {GECCO} 2018, Kyoto, Japan, July 15-19, 2018}, pages = {545--552}, publisher = {{ACM}}, year = {2018}, url = {https://doi.org/10.1145/3205455.3205564}, doi = {10.1145/3205455.3205564}, timestamp = {Wed, 21 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/gecco/Uchibe18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdl-epirob/WangEU18, author = {Jiexin Wang and Stefan Elfwing and Eiji Uchibe}, title = {Deep Reinforcement Learning by Parallelizing Reward and Punishment using the MaxPain Architecture}, booktitle = {2018 Joint {IEEE} 8th International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2018, Tokyo, Japan, September 17-20, 2018}, pages = {175--180}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/DEVLRN.2018.8761044}, doi = {10.1109/DEVLRN.2018.8761044}, timestamp = {Thu, 18 Jul 2019 19:18:02 +0200}, biburl = {https://dblp.org/rec/conf/icdl-epirob/WangEU18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1807-09443, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, title = {Unbounded Output Networks for Classification}, journal = {CoRR}, volume = {abs/1807.09443}, year = {2018}, url = {http://arxiv.org/abs/1807.09443}, eprinttype = {arXiv}, eprint = {1807.09443}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1807-09443.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/finr/WangUD17, author = {Jiexin Wang and Eiji Uchibe and Kenji Doya}, title = {Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer}, journal = {Frontiers Neurorobotics}, volume = {11}, pages = {1}, year = {2017}, url = {https://doi.org/10.3389/fnbot.2017.00001}, doi = {10.3389/FNBOT.2017.00001}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/finr/WangUD17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iconip/ReinkeUD17, author = {Chris Reinke and Eiji Uchibe and Kenji Doya}, editor = {Derong Liu and Shengli Xie and Yuanqing Li and Dongbin Zhao and El{-}Sayed M. El{-}Alfy}, title = {Average Reward Optimization with Multiple Discounting Reinforcement Learners}, booktitle = {Neural Information Processing - 24th International Conference, {ICONIP} 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {10634}, pages = {789--800}, publisher = {Springer}, year = {2017}, url = {https://doi.org/10.1007/978-3-319-70087-8\_81}, doi = {10.1007/978-3-319-70087-8\_81}, timestamp = {Tue, 14 May 2019 10:00:42 +0200}, biburl = {https://dblp.org/rec/conf/iconip/ReinkeUD17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/TsurumineCUM17, author = {Yoshihisa Tsurumine and Yunduan Cui and Eiji Uchibe and Takamitsu Matsubara}, title = {Deep dynamic policy programming for robot control with raw images}, booktitle = {2017 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2017, Vancouver, BC, Canada, September 24-28, 2017}, pages = {1545--1550}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/IROS.2017.8205960}, doi = {10.1109/IROS.2017.8205960}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/TsurumineCUM17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/ElfwingUD17, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, title = {Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning}, journal = {CoRR}, volume = {abs/1702.03118}, year = {2017}, url = {http://arxiv.org/abs/1702.03118}, eprinttype = {arXiv}, eprint = {1702.03118}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/ElfwingUD17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/ElfwingUD17a, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, title = {Online Meta-learning by Parallel Algorithm Competition}, journal = {CoRR}, volume = {abs/1702.07490}, year = {2017}, url = {http://arxiv.org/abs/1702.07490}, eprinttype = {arXiv}, eprint = {1702.07490}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/ElfwingUD17a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1710-10866, author = {Tadashi Kozuno and Eiji Uchibe and Kenji Doya}, title = {Unifying Value Iteration, Advantage Learning, and Dynamic Policy Programming}, journal = {CoRR}, volume = {abs/1710.10866}, year = {2017}, url = {http://arxiv.org/abs/1710.10866}, eprinttype = {arXiv}, eprint = {1710.10866}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1710-10866.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/alr/WangUD16, author = {Jiexin Wang and Eiji Uchibe and Kenji Doya}, title = {EM-based policy hyper parameter exploration: application to standing and balancing of a two-wheeled smartphone robot}, journal = {Artif. Life Robotics}, volume = {21}, number = {1}, pages = {125--131}, year = {2016}, url = {https://doi.org/10.1007/s10015-015-0260-7}, doi = {10.1007/S10015-015-0260-7}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/alr/WangUD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/ElfwingUD16, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, title = {From free energy to expected energy: Improving energy-based value function approximation in reinforcement learning}, journal = {Neural Networks}, volume = {84}, pages = {17--27}, year = {2016}, url = {https://doi.org/10.1016/j.neunet.2016.07.013}, doi = {10.1016/J.NEUNET.2016.07.013}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/ElfwingUD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdl-epirob/HuangUD16, author = {Qiong Huang and Eiji Uchibe and Kenji Doya}, title = {Emergence of communication among reinforcement learning agents under coordination environment}, booktitle = {2016 Joint {IEEE} International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2016, Cergy-Pontoise, France, September 19-22, 2016}, pages = {57--58}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/DEVLRN.2016.7846790}, doi = {10.1109/DEVLRN.2016.7846790}, timestamp = {Wed, 20 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icdl-epirob/HuangUD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iconip/Uchibe16, author = {Eiji Uchibe}, editor = {Akira Hirose and Seiichi Ozawa and Kenji Doya and Kazushi Ikeda and Minho Lee and Derong Liu}, title = {Deep Inverse Reinforcement Learning by Logistic Regression}, booktitle = {Neural Information Processing - 23rd International Conference, {ICONIP} 2016, Kyoto, Japan, October 16-21, 2016, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {9947}, pages = {23--31}, year = {2016}, url = {https://doi.org/10.1007/978-3-319-46687-3\_3}, doi = {10.1007/978-3-319-46687-3\_3}, timestamp = {Tue, 14 May 2019 10:00:42 +0200}, biburl = {https://dblp.org/rec/conf/iconip/Uchibe16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/ElfwingUD15, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, title = {Expected energy-based restricted Boltzmann machine for classification}, journal = {Neural Networks}, volume = {64}, pages = {29--38}, year = {2015}, url = {https://doi.org/10.1016/j.neunet.2014.09.006}, doi = {10.1016/J.NEUNET.2014.09.006}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/ElfwingUD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdl-epirob/UchibeD14, author = {Eiji Uchibe and Kenji Doya}, title = {Inverse reinforcement learning using Dynamic Policy Programming}, booktitle = {4th International Conference on Development and Learning and on Epigenetic Robotics, {ICDL-EPIROB} 2014, Genoa, Italy, October 13-16, 2014}, pages = {222--228}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/DEVLRN.2014.6982985}, doi = {10.1109/DEVLRN.2014.6982985}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icdl-epirob/UchibeD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/UchibeD14, author = {Eiji Uchibe and Kenji Doya}, title = {Combining learned controllers to achieve new goals based on linearly solvable MDPs}, booktitle = {2014 {IEEE} International Conference on Robotics and Automation, {ICRA} 2014, Hong Kong, China, May 31 - June 7, 2014}, pages = {5252--5259}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICRA.2014.6907631}, doi = {10.1109/ICRA.2014.6907631}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/icra/UchibeD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/finr/ElfwingUD13, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, title = {Scaled free-energy based reinforcement learning for robust and efficient learning in high-dimensional state spaces}, journal = {Frontiers Neurorobotics}, volume = {7}, pages = {3}, year = {2013}, url = {https://doi.org/10.3389/fnbot.2013.00003}, doi = {10.3389/FNBOT.2013.00003}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/finr/ElfwingUD13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/finr/KinjoUD13, author = {Ken Kinjo and Eiji Uchibe and Kenji Doya}, title = {Evaluation of linearly solvable Markov decision process with dynamic model learning in a mobile robot navigation task}, journal = {Frontiers Neurorobotics}, volume = {7}, pages = {7}, year = {2013}, url = {https://doi.org/10.3389/fnbot.2013.00007}, doi = {10.3389/FNBOT.2013.00007}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/finr/KinjoUD13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdl-epirob/YoshidaUD13, author = {Naoto Yoshida and Eiji Uchibe and Kenji Doya}, title = {Reinforcement learning with state-dependent discount factor}, booktitle = {2013 {IEEE} Third Joint International Conference on Development and Learning and Epigenetic Robotics, {ICDL-EPIROB} 2013, Osaka, Japan, August 18-22, 2013}, pages = {1--6}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/DevLrn.2013.6652533}, doi = {10.1109/DEVLRN.2013.6652533}, timestamp = {Sun, 25 Oct 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icdl-epirob/YoshidaUD13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/adb/ElfwingUDC11, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya and Henrik I. Christensen}, title = {Darwinian embodied evolution of the learning ability for survival}, journal = {Adapt. Behav.}, volume = {19}, number = {2}, pages = {101--120}, year = {2011}, url = {https://doi.org/10.1177/1059712310397633}, doi = {10.1177/1059712310397633}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/adb/ElfwingUDC11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/neco/MorimuraUYPD10, author = {Tetsuro Morimura and Eiji Uchibe and Junichiro Yoshimoto and Jan Peters and Kenji Doya}, title = {Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning}, journal = {Neural Comput.}, volume = {22}, number = {2}, pages = {342--376}, year = {2010}, url = {https://doi.org/10.1162/neco.2009.12-08-922}, doi = {10.1162/NECO.2009.12-08-922}, timestamp = {Tue, 01 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/neco/MorimuraUYPD10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iconip/ElfwingOUD10, author = {Stefan Elfwing and Makoto Otsuka and Eiji Uchibe and Kenji Doya}, editor = {Kok Wai Wong and B. Sumudu U. Mendis and Abdesselam Bouzerdoum}, title = {Free-Energy Based Reinforcement Learning for Vision-Based Navigation with High-Dimensional Sensory Inputs}, booktitle = {Neural Information Processing. Theory and Algorithms - 17th International Conference, {ICONIP} 2010, Sydney, Australia, November 22-25, 2010, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {6443}, pages = {215--222}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-17537-4\_27}, doi = {10.1007/978-3-642-17537-4\_27}, timestamp = {Tue, 14 May 2019 10:00:42 +0200}, biburl = {https://dblp.org/rec/conf/iconip/ElfwingOUD10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iconip/ElfwingUD09, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, editor = {Chi{-}Sing Leung and Minho Lee and Jonathan Hoyin Chan}, title = {Emergence of Different Mating Strategies in Artificial Embodied Evolution}, booktitle = {Neural Information Processing, 16th International Conference, {ICONIP} 2009, Bangkok, Thailand, December 1-5, 2009, Proceedings, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {5864}, pages = {638--647}, publisher = {Springer}, year = {2009}, url = {https://doi.org/10.1007/978-3-642-10684-2\_71}, doi = {10.1007/978-3-642-10684-2\_71}, timestamp = {Tue, 14 May 2019 10:00:42 +0200}, biburl = {https://dblp.org/rec/conf/iconip/ElfwingUD09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/MorimuraUYD09, author = {Tetsuro Morimura and Eiji Uchibe and Junichiro Yoshimoto and Kenji Doya}, editor = {Yoshua Bengio and Dale Schuurmans and John D. Lafferty and Christopher K. I. Williams and Aron Culotta}, title = {A Generalized Natural Actor-Critic Algorithm}, booktitle = {Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, Vancouver, British Columbia, Canada}, pages = {1312--1320}, publisher = {Curran Associates, Inc.}, year = {2009}, url = {https://proceedings.neurips.cc/paper/2009/hash/acf4b89d3d503d8252c9c4ba75ddbf6d-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/MorimuraUYD09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:series/lncs/ElfwingUD09, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, editor = {Bernhard Sendhoff and Edgar K{\"{o}}rner and Olaf Sporns and Helge J. Ritter and Kenji Doya}, title = {Co-evolution of Rewards and Meta-parameters in Embodied Evolution}, booktitle = {Creating Brain-Like Intelligence: From Basic Principles to Complex Intelligent Systems}, series = {Lecture Notes in Computer Science}, volume = {5436}, pages = {278--302}, publisher = {Springer}, year = {2009}, url = {https://doi.org/10.1007/978-3-642-00616-6\_13}, doi = {10.1007/978-3-642-00616-6\_13}, timestamp = {Tue, 14 May 2019 10:00:55 +0200}, biburl = {https://dblp.org/rec/series/lncs/ElfwingUD09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/adb/ElfwingUDC08, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya and Henrik I. Christensen}, title = {Co-evolution of Shaping Rewards and Meta-Parameters in Reinforcement Learning}, journal = {Adapt. Behav.}, volume = {16}, number = {6}, pages = {400--412}, year = {2008}, url = {https://doi.org/10.1177/1059712308092835}, doi = {10.1177/1059712308092835}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/adb/ElfwingUDC08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/alr/SatoUD08, author = {Takashi Sato and Eiji Uchibe and Kenji Doya}, title = {Learning how, what, and whether to communicate: emergence of protocommunication in reinforcement learning agents}, journal = {Artif. Life Robotics}, volume = {12}, number = {1-2}, pages = {70--74}, year = {2008}, url = {https://doi.org/10.1007/s10015-007-0444-x}, doi = {10.1007/S10015-007-0444-X}, timestamp = {Tue, 01 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/alr/SatoUD08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/alr/MorimuraUD08, author = {Tetsuro Morimura and Eiji Uchibe and Kenji Doya}, title = {Natural actor-critic with baseline adjustment for variance reduction}, journal = {Artif. Life Robotics}, volume = {13}, number = {1}, pages = {275--279}, year = {2008}, url = {https://doi.org/10.1007/s10015-008-0514-8}, doi = {10.1007/S10015-008-0514-8}, timestamp = {Mon, 30 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/alr/MorimuraUD08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/UchibeD08, author = {Eiji Uchibe and Kenji Doya}, title = {Finding intrinsic rewards by embodied evolution and constrained reinforcement learning}, journal = {Neural Networks}, volume = {21}, number = {10}, pages = {1447--1455}, year = {2008}, url = {https://doi.org/10.1016/j.neunet.2008.09.013}, doi = {10.1016/J.NEUNET.2008.09.013}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/UchibeD08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iconip/KamiokaUD09, author = {Takumi Kamioka and Eiji Uchibe and Kenji Doya}, editor = {Mario K{\"{o}}ppen and Nikola K. Kasabov and George G. Coghill}, title = {NeuroEvolution Based on Reusable and Hierarchical Modular Representation}, booktitle = {Advances in Neuro-Information Processing, 15th International Conference, {ICONIP} 2008, Auckland, New Zealand, November 25-28, 2008, Revised Selected Papers, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {5506}, pages = {22--31}, publisher = {Springer}, year = {2008}, url = {https://doi.org/10.1007/978-3-642-02490-0\_3}, doi = {10.1007/978-3-642-02490-0\_3}, timestamp = {Tue, 14 May 2019 10:00:42 +0200}, biburl = {https://dblp.org/rec/conf/iconip/KamiokaUD09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/pkdd/MorimuraUYD08, author = {Tetsuro Morimura and Eiji Uchibe and Junichiro Yoshimoto and Kenji Doya}, editor = {Walter Daelemans and Bart Goethals and Katharina Morik}, title = {A New Natural Policy Gradient by Stationary Distribution Metric}, 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 = {82--97}, publisher = {Springer}, year = {2008}, url = {https://doi.org/10.1007/978-3-540-87481-2\_6}, doi = {10.1007/978-3-540-87481-2\_6}, timestamp = {Mon, 16 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/pkdd/MorimuraUYD08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tec/ElfwingUDC07, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya and Henrik I. Christensen}, title = {Evolutionary Development of Hierarchical Learning Structures}, journal = {{IEEE} Trans. Evol. Comput.}, volume = {11}, number = {2}, pages = {249--264}, year = {2007}, url = {https://doi.org/10.1109/TEVC.2006.890270}, doi = {10.1109/TEVC.2006.890270}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tec/ElfwingUDC07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iconip/UchibeD07, author = {Eiji Uchibe and Kenji Doya}, editor = {Masumi Ishikawa and Kenji Doya and Hiroyuki Miyamoto and Takeshi Yamakawa}, title = {Finding Exploratory Rewards by Embodied Evolution and Constrained Reinforcement Learning in the Cyber Rodents}, booktitle = {Neural Information Processing, 14th International Conference, {ICONIP} 2007, Kitakyushu, Japan, November 13-16, 2007, Revised Selected Papers, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {4985}, pages = {167--176}, publisher = {Springer}, year = {2007}, url = {https://doi.org/10.1007/978-3-540-69162-4\_18}, doi = {10.1007/978-3-540-69162-4\_18}, timestamp = {Tue, 14 May 2019 10:00:42 +0200}, biburl = {https://dblp.org/rec/conf/iconip/UchibeD07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pieee/UchibeA06, author = {Eiji Uchibe and Minoru Asada}, title = {Incremental Coevolution With Competitive and Cooperative Tasks in a Multirobot Environment}, journal = {Proc. {IEEE}}, volume = {94}, number = {7}, pages = {1412--1424}, year = {2006}, url = {https://doi.org/10.1109/JPROC.2006.876918}, doi = {10.1109/JPROC.2006.876918}, timestamp = {Fri, 02 Oct 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pieee/UchibeA06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/adb/DoyaU05, author = {Kenji Doya and Eiji Uchibe}, title = {The Cyber Rodent Project: Exploration of Adaptive Mechanisms for Self-Preservation and Self-Reproduction}, journal = {Adapt. Behav.}, volume = {13}, number = {2}, pages = {149--160}, year = {2005}, url = {https://doi.org/10.1177/105971230501300206}, doi = {10.1177/105971230501300206}, timestamp = {Tue, 25 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/adb/DoyaU05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cec/ElfwingUDC05, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya and Henrik I. Christensen}, title = {Biologically inspired embodied evolution of survival}, booktitle = {Proceedings of the {IEEE} Congress on Evolutionary Computation, {CEC} 2005, 2-4 September 2005, Edinburgh, {UK}}, pages = {2210--2216}, publisher = {{IEEE}}, year = {2005}, url = {https://doi.org/10.1109/CEC.2005.1554969}, doi = {10.1109/CEC.2005.1554969}, timestamp = {Thu, 16 Dec 2021 13:59:05 +0100}, biburl = {https://dblp.org/rec/conf/cec/ElfwingUDC05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ElfwingUDC04, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya and Henrik I. Christensen}, title = {Multi-agent reinforcement learning: using macro actions to learn a mating task}, booktitle = {2004 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, Sendai, Japan, September 28 - October 2, 2004}, pages = {3164--3169}, publisher = {{IEEE}}, year = {2004}, url = {https://doi.org/10.1109/IROS.2004.1389904}, doi = {10.1109/IROS.2004.1389904}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/ElfwingUDC04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/gecco/ElfwingUD03, author = {Stefan Elfwing and Eiji Uchibe and Kenji Doya}, editor = {Erick Cant{\'{u}}{-}Paz and James A. Foster and Kalyanmoy Deb and Lawrence Davis and Rajkumar Roy and Una{-}May O'Reilly and Hans{-}Georg Beyer and Russell K. Standish and Graham Kendall and Stewart W. Wilson and Mark Harman and Joachim Wegener and Dipankar Dasgupta and Mitchell A. Potter and Alan C. Schultz and Kathryn A. Dowsland and Natasa Jonoska and Julian F. Miller}, title = {An Evolutionary Approach to Automatic Construction of the Structure in Hierarchical Reinforcement Learning}, booktitle = {Genetic and Evolutionary Computation - {GECCO} 2003, Genetic and Evolutionary Computation Conference, Chicago, IL, USA, July 12-16, 2003. Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {2723}, pages = {507--509}, publisher = {Springer}, year = {2003}, url = {https://doi.org/10.1007/3-540-45105-6\_62}, doi = {10.1007/3-540-45105-6\_62}, timestamp = {Tue, 14 May 2019 10:00:35 +0200}, biburl = {https://dblp.org/rec/conf/gecco/ElfwingUD03.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ras/UchibeYA02, author = {Eiji Uchibe and Masakazu Yanase and Minoru Asada}, title = {Behavior generation for a mobile robot based on the adaptive fitness function}, journal = {Robotics Auton. Syst.}, volume = {40}, number = {2-3}, pages = {69--77}, year = {2002}, url = {https://doi.org/10.1016/S0921-8890(02)00232-4}, doi = {10.1016/S0921-8890(02)00232-4}, timestamp = {Mon, 24 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ras/UchibeYA02.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ngc/AsadaU01, author = {Minoru Asada and Eiji Uchibe}, title = {Multiagent Learning towards RoboCup}, journal = {New Gener. Comput.}, volume = {19}, number = {2}, pages = {103--120}, year = {2001}, url = {https://doi.org/10.1007/BF03037249}, doi = {10.1007/BF03037249}, timestamp = {Thu, 14 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ngc/AsadaU01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/UchibeKHA01, author = {Eiji Uchibe and Tatsunori Kato and Koh Hosoda and Minoru Asada}, title = {Dynamic Task Assignment in a Multiagent/Multitask Environment based on Module Conflict Resolution}, booktitle = {Proceedings of the 2001 {IEEE} International Conference on Robotics and Automation, {ICRA} 2001, May 21-26, 2001, Seoul, Korea}, pages = {3987--3992}, publisher = {{IEEE}}, year = {2001}, url = {https://doi.org/10.1109/ROBOT.2001.933240}, doi = {10.1109/ROBOT.2001.933240}, timestamp = {Mon, 04 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/UchibeKHA01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/robocup/UchibeYA01, author = {Eiji Uchibe and Masakazu Yanase and Minoru Asada}, editor = {Andreas Birk and Silvia Coradeschi and Satoshi Tadokoro}, title = {Evolutionary Behavior Selection with Activation/Termination Constraints}, booktitle = {RoboCup 2001: Robot Soccer World Cup {V}}, series = {Lecture Notes in Computer Science}, volume = {2377}, pages = {234--243}, publisher = {Springer}, year = {2001}, url = {https://doi.org/10.1007/3-540-45603-1\_24}, doi = {10.1007/3-540-45603-1\_24}, timestamp = {Tue, 14 May 2019 10:00:53 +0200}, biburl = {https://dblp.org/rec/conf/robocup/UchibeYA01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/robocup/TakahashiUTYIIA00, author = {Yasutake Takahashi and Eiji Uchibe and Takahashi Tamura and Masakazu Yanase and Shoichi Ikenoue and Shujiro Inui and Minoru Asada}, editor = {Peter Stone and Tucker R. Balch and Gerhard K. Kraetzschmar}, title = {Osaka University "Trackies 2000"}, booktitle = {RoboCup 2000: Robot Soccer World Cup {IV}}, series = {Lecture Notes in Computer Science}, volume = {2019}, pages = {607--610}, publisher = {Springer}, year = {2000}, url = {https://doi.org/10.1007/3-540-45324-5\_98}, doi = {10.1007/3-540-45324-5\_98}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/robocup/TakahashiUTYIIA00.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ai/AsadaUH99, author = {Minoru Asada and Eiji Uchibe and Koh Hosoda}, title = {Cooperative Behavior Acquisition for Mobile Robots in Dynamically Changing Real Worlds Via Vision-Based Reinforcement Learning and Development}, journal = {Artif. Intell.}, volume = {110}, number = {2}, pages = {275--292}, year = {1999}, url = {https://doi.org/10.1016/S0004-3702(99)00026-0}, doi = {10.1016/S0004-3702(99)00026-0}, timestamp = {Mon, 04 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ai/AsadaUH99.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/robocup/UchibeA99, author = {Eiji Uchibe and Minoru Asada}, editor = {Manuela M. Veloso and Enrico Pagello and Hiroaki Kitano}, title = {Multiple Reward Criterion for Cooperative Behavior Acquisition in a Muliagent Environment}, booktitle = {RoboCup-99: Robot Soccer World Cup {III}}, series = {Lecture Notes in Computer Science}, volume = {1856}, pages = {519--530}, publisher = {Springer}, year = {1999}, url = {https://doi.org/10.1007/3-540-45327-X\_44}, doi = {10.1007/3-540-45327-X\_44}, timestamp = {Tue, 14 May 2019 10:00:53 +0200}, biburl = {https://dblp.org/rec/conf/robocup/UchibeA99.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/robocup/SuzukiKIKTYTUA99, author = {Sho'ji Suzuki and Tatsunori Kato and Hiroshi Ishizuka and Hiroyoshi Kawanishi and Takashi Tamura and Masakazu Yanase and Yasutake Takahashi and Eiji Uchibe and Minoru Asada}, editor = {Manuela M. Veloso and Enrico Pagello and Hiroaki Kitano}, title = {The Team Description of Osaka University "Trackies-99"}, booktitle = {RoboCup-99: Robot Soccer World Cup {III}}, series = {Lecture Notes in Computer Science}, volume = {1856}, pages = {750--753}, publisher = {Springer}, year = {1999}, url = {https://doi.org/10.1007/3-540-45327-X\_97}, doi = {10.1007/3-540-45327-X\_97}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/robocup/SuzukiKIKTYTUA99.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/aim/AsadaSTUNMIK98, author = {Minoru Asada and Sho'ji Suzuki and Yasutake Takahashi and Eiji Uchibe and Masateru Nakamura and Chizuko Mishima and Hiroshi Ishizuka and Tatsunori Kato}, title = {{TRACKIES:} RoboCup-97 Middle-Size League World Cochampion}, journal = {{AI} Mag.}, volume = {19}, number = {3}, pages = {71--78}, year = {1998}, url = {https://doi.org/10.1609/aimag.v19i3.1395}, doi = {10.1609/AIMAG.V19I3.1395}, timestamp = {Tue, 25 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/aim/AsadaSTUNMIK98.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/UchibeAH98, author = {Eiji Uchibe and Minoru Asada and Koh Hosoda}, title = {State Space Construction for Behavior Acquisition in Multi Agent Environments with Vision and Action}, booktitle = {Proceedings of the Sixth International Conference on Computer Vision (ICCV-98), Bombay, India, January 4-7, 1998}, pages = {870--875}, publisher = {{IEEE} Computer Society}, year = {1998}, url = {https://doi.org/10.1109/ICCV.1998.710819}, doi = {10.1109/ICCV.1998.710819}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccv/UchibeAH98.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/UchibeAH98, author = {Eiji Uchibe and Minoru Asada and Koh Hosoda}, title = {Cooperative Behavior Acquisition in Multi Mobile Robots Environment by Reinforcement Learning Based on State Vector Estimation}, booktitle = {Proceedings of the {IEEE} International Conference on Robotics and Automation, ICRA-98, Leuven, Belgium, May 16-20, 1998}, pages = {1558--1563}, publisher = {{IEEE} Computer Society}, year = {1998}, url = {https://doi.org/10.1109/ROBOT.1998.677351}, doi = {10.1109/ROBOT.1998.677351}, timestamp = {Mon, 04 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/UchibeAH98.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/UchibeAH98a, author = {Eiji Uchibe and Minoru Asada and Koh Hosoda}, title = {Environmental Complexity Control for Vision-Based Learning Mobile Robot}, booktitle = {Proceedings of the {IEEE} International Conference on Robotics and Automation, ICRA-98, Leuven, Belgium, May 16-20, 1998}, pages = {1865--1870}, publisher = {{IEEE} Computer Society}, year = {1998}, url = {https://doi.org/10.1109/ROBOT.1998.680514}, doi = {10.1109/ROBOT.1998.680514}, timestamp = {Mon, 04 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/UchibeAH98a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/UchibeNA98, author = {Eiji Uchibe and Masateru Nakamura and Minoru Asada}, title = {Co-evolution for cooperative behavior acquisition in a multiple mobile robot environment}, booktitle = {Proceedings 1998 {IEEE/RSJ} International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications, October 13-17, 1998, Victoria, BC, Canada}, pages = {425--430}, publisher = {{IEEE}}, year = {1998}, url = {https://doi.org/10.1109/IROS.1998.724656}, doi = {10.1109/IROS.1998.724656}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/UchibeNA98.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/robocup/UchibeNA98, author = {Eiji Uchibe and Masateru Nakamura and Minoru Asada}, editor = {Minoru Asada and Hiroaki Kitano}, title = {Cooperative Behavior Acquisition in a Multiple Mobile Robot Environment by Co-evolution}, booktitle = {RoboCup-98: Robot Soccer World Cup {II}}, series = {Lecture Notes in Computer Science}, volume = {1604}, pages = {273--285}, publisher = {Springer}, year = {1998}, url = {https://doi.org/10.1007/3-540-48422-1\_22}, doi = {10.1007/3-540-48422-1\_22}, timestamp = {Tue, 14 May 2019 10:00:53 +0200}, biburl = {https://dblp.org/rec/conf/robocup/UchibeNA98.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/robocup/SuzukiKITUA98, author = {Sho'ji Suzuki and Tatsunori Kato and Hiroshi Ishizuka and Yasutake Takahashi and Eiji Uchibe and Minoru Asada}, editor = {Minoru Asada and Hiroaki Kitano}, title = {An Application of Vision-Based Learning in RoboCup for a Real Robot with an Omnidirectional Vision System and the Team Description of Osaka University "Trackies"}, booktitle = {RoboCup-98: Robot Soccer World Cup {II}}, series = {Lecture Notes in Computer Science}, volume = {1604}, pages = {316--325}, publisher = {Springer}, year = {1998}, url = {https://doi.org/10.1007/3-540-48422-1\_25}, doi = {10.1007/3-540-48422-1\_25}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/robocup/SuzukiKITUA98.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ewlr/UchibeAH97, author = {Eiji Uchibe and Minoru Asada and Koh Hosoda}, editor = {Andreas Birk and John Demiris}, title = {Vision Based State Space Construction for Learning Mobile Robots in Multi-agent Environments}, booktitle = {Learning Robots, 6th European Workshop, EWLR-6, Brighton, England, UK, August 1-2, 1997, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {1545}, pages = {62--78}, publisher = {Springer}, year = {1997}, url = {https://doi.org/10.1007/3-540-49240-2\_5}, doi = {10.1007/3-540-49240-2\_5}, timestamp = {Mon, 04 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ewlr/UchibeAH97.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/robocup/SuzukiTUNMIKA97, author = {Sho'ji Suzuki and Yasutake Takahashi and Eiji Uchibe and Masateru Nakamura and Chizuko Mishima and Hiroshi Ishizuka and Tatsunori Kato and Minoru Asada}, editor = {Hiroaki Kitano}, title = {Vision-Based Robot Learning Towards RoboCup: Osaka University "Trackies"}, booktitle = {RoboCup-97: Robot Soccer World Cup {I}}, series = {Lecture Notes in Computer Science}, volume = {1395}, pages = {305--319}, publisher = {Springer}, year = {1997}, url = {https://doi.org/10.1007/3-540-64473-3\_69}, doi = {10.1007/3-540-64473-3\_69}, timestamp = {Tue, 14 May 2019 10:00:53 +0200}, biburl = {https://dblp.org/rec/conf/robocup/SuzukiTUNMIKA97.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/UchibeAH96, author = {Eiji Uchibe and Minoru Asada and Koh Hosoda}, title = {Behavior coordination for a mobile robot using modular reinforcement learning}, booktitle = {Proceedings of {IEEE/RSJ} International Conference on Intelligent Robots and Systems. {IROS} 1996, November 4-8, 1996, Osaka, Japan}, pages = {1329--1336}, publisher = {{IEEE}}, year = {1996}, url = {https://doi.org/10.1109/IROS.1996.568989}, doi = {10.1109/IROS.1996.568989}, timestamp = {Mon, 04 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/UchibeAH96.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/AsadaUNTH94, author = {Minoru Asada and Eiji Uchibe and Shoichi Noda and Sukoya Tawaratsumida and Koh Hosoda}, title = {Coordination of multiple behaviors acquired by a vision-based reinforcement learning}, booktitle = {Proceedings of {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 1994, September 12 - 16, 1994, Munich, Germany}, pages = {917--924}, publisher = {{IEEE}}, year = {1994}, url = {https://doi.org/10.1109/IROS.1994.407484}, doi = {10.1109/IROS.1994.407484}, timestamp = {Mon, 04 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/AsadaUNTH94.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.