| Presentation | 2019-06-18 Hybrid Reinforcement and Imitation Learning for Human-Like Agents Rousslan Fernand Julien Dossa, Xinyu Lian, Hirokazu Nomoto, Takashi Matsubara, Kuniaki Uehara, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Reinforcement learning methods achieve performance superior to humans in a wide range of complex tasks and uncertain environments. However, high performance is not the sole metric for practical use, namely when used as a game AI or autonomous driving agent, since highly efficient agent tends to perform greedily and selfishly, therefore inconveniencing the users. Consequently, there is a need for more human-like agents. Imitation learning, on the other hand, aims at reproducing the behavior of a human expert and can be used to train a human-like agent, the caveat being that its performance is generally limited by the expert's skill. In the study, we propose a training scheme to construct a human-like and efficient agent through a hybrid of reinforcement and imitation learning, and apply it to a racing car simulator. The proposed hybrid agent achieves a higher performance than a strictly imitation learning agent while exhibits more human-like behavior, which is measured via a human sensitivity test. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Autonomous Driving / Game AI / Human-Like Behavior / Imitation Learning / Reinforcement Learning |
| Paper # | NC2019-16,IBISML2019-14 |
| Date of Issue | 2019-06-10 (NC, IBISML) |
| Conference Information | |
| Committee | NC / IBISML / IPSJ-MPS / IPSJ-BIO |
|---|---|
| Conference Date | 2019/6/17(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Okinawa Institute of Science and Technology |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Neurocomputing, Machine Learning Approach to Biodata Mining, and General |
| Chair | Hayaru Shouno(UEC) / Hisashi Kashima(Kyoto Univ.) / Masakazu Sekijima(Tokyo Tech) / Hiroyuki Kurata(Kyutech) |
| Vice Chair | Kazuyuki Samejima(Tamagawa Univ) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Kazuyuki Samejima(NAIST) / Masashi Sugiyama(NTT) / Koji Tsuda(Nagoya Inst. of Tech.) / (AIST) / (Nagoya Univ.) |
| Assistant | Takashi Shinozaki(NICT) / Ken Takiyama(TUAT) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Neurocomputing / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / IPSJ Special Interest Group on Mathematical Modeling and Problem Solving / IPSJ Special Interest Group on Bioinformatics and Genomics |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Hybrid Reinforcement and Imitation Learning for Human-Like Agents |
| Sub Title (in English) | |
| Keyword(1) | Autonomous Driving |
| Keyword(2) | Game AI |
| Keyword(3) | Human-Like Behavior |
| Keyword(4) | Imitation Learning |
| Keyword(5) | Reinforcement Learning |
| 1st Author's Name | Rousslan Fernand Julien Dossa |
| 1st Author's Affiliation | Kobe University(Kobe Uni) |
| 2nd Author's Name | Xinyu Lian |
| 2nd Author's Affiliation | Kobe University(Kobe Uni) |
| 3rd Author's Name | Hirokazu Nomoto |
| 3rd Author's Affiliation | EQUOS RESEARCH Co., Ltd.(*) |
| 4th Author's Name | Takashi Matsubara |
| 4th Author's Affiliation | Kobe University(Kobe Uni) |
| 5th Author's Name | Kuniaki Uehara |
| 5th Author's Affiliation | Kobe University(Kobe Uni) |
| Date | 2019-06-18 |
| Paper # | NC2019-16,IBISML2019-14 |
| Volume (vol) | vol.119 |
| Number (no) | NC-88,IBISML-89 |
| Page | pp.pp.69-74(NC), pp.91-96(IBISML), |
| #Pages | 6 |
| Date of Issue | 2019-06-10 (NC, IBISML) |