|
Affiliation Department |
情報工学科 知能情報分野
|
|
Title |
Associate Professor |
|
External Link |
|
MORIYAMA KOICHI
|
|
|
Research Interests
-
Artificial Intelligence
-
Reinforcement Learning
-
Autonomous Agents
-
Multi-agent Systems
-
Game Theory
Research Areas
-
Informatics / Intelligent informatics
-
Informatics / Soft computing
-
Informatics / Entertainment and game informatics
From School
-
Tokyo Institute of Technology Faculty of Engineering Department of Computer Science Graduated
1994.04 - 1998.03
Country：Japan
From Graduate School
-
Tokyo Institute of Technology Graduate School of Information Science and Engineering Department of Computer Science Master's Course Completed
1998.04 - 2000.03
Country：Japan
-
Tokyo Institute of Technology Graduate School of Information Science and Engineering Department of Computer Science Doctor's Course Completed
2000.04 - 2003.03
Country：Japan
External Career
-
Tokyo Institute of Technology Graduate School of Information Science and Engineering Research Assistant
2003.04 - 2005.03
Country：Japan
-
Osaka University The Institute of Scientific and Industrial Research Research Assistant
2005.04 - 2007.03
Country：Japan
-
Osaka University The Institute of Scientific and Industrial Research Assistant Professor
2007.04 - 2015.03
Country：Japan
-
Osaka University The Institute of Scientific and Industrial Research Specially Appointed Associate Professor
2015.04 - 2015.07
Country：Japan
Professional Memberships
-
The Japanese Society for Artificial Intelligence
2001.08
-
The Institute of Electronics, Information and Communication Engineers
2009.01
Papers
-
Discarding Erroneous Knowledge Online in Transfer Reinforcement Learning Reviewed International journal
Otoya Notsu, Koichi Moriyama, Kosuke Shima, Tohgoroh Matsui, Atsuko Mutoh, Nobuhiro Inuzuka
Proceedings of the 25th International Conference on Principles and Practice of Multi-Agent Systems (PRIMA) 2024.11
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Springer
-
A Simple Sequential Social Dilemma Game Reviewed International journal
Ryoichi Takatsuka, Koichi Moriyama, Tohgoroh Matsui, Atsuko Mutoh, Kosuke Shima, Nobuhiro Inuzuka
Proceedings of the 7th IEEE International Conference on Agents (ICA) 9 - 14 2023.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE
-
Effect of Curiosity-driven Search in Multi-agent Deep Reinforcement Learning Reviewed
Toru Iwashina, Koichi Moriyama, Tohgoroh Matsui, Atsuko Mutoh, Nobuhiro Inuzuka
IPSJ Transactions on Mathematical Modeling and its Applications 16 ( 2 ) 80 - 90 2023.10
Authorship：Corresponding author Language：Japanese Publishing type：Research paper (scientific journal) Publisher：The Information Processing Society of Japan
Other Link： http://id.nii.ac.jp/1001/00228751/
-
Exploration Improvement by Sequential Intrinsic Reward Generator in Deep Reinforcement Learning Reviewed
Kazuhiro Murakami, Koichi Moriyama, Tohgoroh Matsui, Atsuko Mutoh, Nobuhiro Inuzuka
IPSJ Transactions on Mathematical Modeling and its Applications 14 ( 1 ) 1 - 11 2021.01
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：The Information Processing Society of Japan
Other Link： http://id.nii.ac.jp/1001/00209230/
-
Running Reinforcement Learning Agents on GPU for Many Simulations of Two-Person Simultaneous Games Reviewed International journal
Koichi Moriyama, Yoshiya Kurogi, Atsuko Mutoh, Tohgoroh Matsui, Nobuhiro Inuzuka
Proceedings of the 4th IEEE International Conference on Agents (ICA) 50 - 55 2019.10
Authorship：Lead author Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE
-
Multi-objective safe reinforcement learning: the relationship between multi-objective reinforcement learning and safe reinforcement learning Reviewed International journal
Naoto Horie, Tohgoroh Matsui, Koichi Moriyama, Atsuko Mutoh, Nobuhiro Inuzuka
Artificial Life and Robotics 24 ( 3 ) 352 - 359 2019.09
Language：English Publishing type：Research paper (scientific journal) Publisher：Springer
-
Accelerating Deep Q Network by Weighting Experiences Reviewed International journal
Kazuhiro Murakami, Koichi Moriyama, Atsuko Mutoh, Tohgoroh Matsui, Nobuhiro Inuzuka
Proceedings of the 25th International Conference on Neural Information Processing (ICONIP) 1 204 - 213 2018.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Springer
-
Evolution Direction of Reward Appraisal in Reinforcement Learning Agents Reviewed International journal
Masaya Miyawaki, Koichi Moriyama, Atsuko Mutoh, Tohgoroh Matsui, Nobuhiro Inuzuka
Proceedings of the 12th KES International Conference on Agent and Multi-agent Systems: Technologies and Applications (KES-AMSTA) 13 - 22 2018.06
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Springer
-
Two-Stage Reinforcement Learning Algorithm for Quick Cooperation in Repeated Games Invited Reviewed International journal
Wataru Fujita, Koichi Moriyama, Ken-ichi Fukui, Masayuki Numao
Transactions on Computational Collective Intelligence 28 48 - 65 2018.04
Language：English Publishing type：Research paper (scientific journal) Publisher：Springer
-
The Resilience of Cooperation in a Dilemma Game Played by Reinforcement Learning Agents Reviewed International journal
Koichi Moriyama, Kaori Nakase, Atsuko Mutoh, and Nobuhiro Inuzuka
Proceedings of the 2nd International Conference on Agents (ICA) 33 - 39 2017.07
Authorship：Lead author Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE
Misc
-
Forming "Personal Values": Constructive Approach by Using Artificial Agents
Koichi Moriyama
Manufacturing & Technology 65 ( 4 ) 84 - 86 2013.10
Authorship：Lead author Language：Japanese Publishing type：Rapid communication, short report, research note, etc. (scientific journal) Publisher：Association for the Advancement of Manufacturing and Technology
Other Link： http://seisan.server-shared.com/654/654-84.pdf
-
オーエンス・ルイス：アンビエント環境制御を用いた知的オフィスチェアの提案
清川清, 畠中理英, 細田一史, 岡田雅司, 繁田浩功, 石原靖哲, 大下福仁, 角川裕次, 栗原聡, 森山甲一
Systems, Control and Information 56 ( 1 ) 14 - 20 2012.01
Language：Japanese Publishing type：Article, review, commentary, editorial, etc. (scientific journal) Publisher：システム制御情報学会
Presentations
-
Learning to Avoid Multiple Moving Obstacles Using Artificial Dangerous Fields
Fuma Kondo, Koichi Moriyama, Atsuko Mutoh, Kosuke Shima, Tohgoroh Matsui, Nobuhiro Inuzuka
The 215th IPSJ SIG on Intelligent Computing Systems 2024.09 The Information Processing Society of Japan
Event date： 2024.09
Language：Japanese Presentation type：Oral presentation (general)
Venue：Fukui Country：Japan
Other Link： http://id.nii.ac.jp/1001/00238937/
-
Identifying useful appraisal functions in a multi-agent reinforcement learning environment
Yoshitaka Isobe, Koichi Moriyama, Atsuko Mutoh, Kosuke Shima, Tohgoroh Matsui, Nobuhiro Inuzuka
The 38th Annual Conference of the Japanese Society for Artificial Intelligence 2024.05 Japanese Society for Aritficial Intelligence
Event date： 2024.05
Language：Japanese Presentation type：Oral presentation (general)
Venue：Hamamatsu Country：Japan
-
Acquisition of Cooperative Behavior Using Curriculum Learning in Geometry Friends
Yoshito Kajino, Koichi Moriyama, Kosuke Shima, Tohgoroh Matsui, Atsuko Mutoh, Nobuhiro Inuzuka
The 51st IPSJ SIG on Game Informatics 2024.03 The Information Processing Society of Japan
Event date： 2024.03
Language：Japanese Presentation type：Oral presentation (general)
Venue：Tokyo Country：Japan
Other Link： http://id.nii.ac.jp/1001/00232795/
-
Applying Degree of Contribution to Curiosity-driven Search for Multi-agent Pursuit of Learning Preys
Yutatsu Inagaki, Koichi Moriyama, Atsuko Mutoh, Kosuke Shima, Tohgoroh Matsui, Nobuhiro Inuzuka
The 212th IPSJ SIG on Intelligent Computing Systems 2024.02 The Information Processing Society of Japan
Event date： 2024.02
Language：Japanese Presentation type：Oral presentation (general)
Venue：Nagoya Country：Japan
Other Link： http://id.nii.ac.jp/1001/00232561/
-
Generalization of the state space for cooperation in similar situations of a heterogeneous multi-agent environment
Yuta Usuki, Koichi Moriyama, Atsuko Mutoh, Tohgoroh Matsui, Nobuhiro Inuzuka
The 37th Annual Conference of the Japanese Society for Artificial Intelligence 2023.06 Japanese Society for Aritficial Intelligence
Event date： 2023.06
Language：Japanese Presentation type：Oral presentation (general)
Venue：Kumamoto Country：Japan
-
Potential field generation for distance-based intrinsic rewards
Hikaru Nakada, Koichi Moriyama, Atsuko Mutoh, Tohgoroh Matsui, Nobuhiro Inuzuka
The 208th IPSJ SIG on Intelligent Computing Systems 2023.02 The Information Processing Society of Japan
Event date： 2023.02
Language：Japanese Presentation type：Oral presentation (general)
Venue：Nagoya Country：Japan
Other Link： http://id.nii.ac.jp/1001/00224075/
-
Optimization of subjective utility to derive cooperative actions in a prisoner’s dilemma environment
Ryoichi Takatsuka, Koichi Moriyama, Atsuko Mutoh, Tohgoroh Matsui, Nobuhiro Inuzuka
The 36th Annual Conference of the Japanese Society for Artificial Intelligence 2022.06 Japanese Society for Aritficial Intelligence
Event date： 2022.06
Language：Japanese Presentation type：Oral presentation (general)
Venue：Kyoto Country：Japan
-
Curiosity-Driven Search in a Multiagent Reinforcement Learning Problem
Toru Iwashina, Koichi Moriyama, Tohgoroh Matsui, Atsuko Mutoh, Nobuhiro Inuzuka
The 35th Annual Conference of the Japanese Society for Artificial Intelligence 2021.06 Japanese Society for Aritficial Intelligence
Event date： 2021.06
Language：Japanese Presentation type：Oral presentation (general)
Venue：Online
-
Intelligent Agents with "Personal Values" Invited International conference
Koichi Moriyama
The 10th Japanese-German Frontiers of Science (JGFoS) Symposium
Event date： 2013.11
Language：English Presentation type：Poster presentation
Venue：Kyoto Country：Japan
-
Does Profit Mean Happiness? — A way to create an emotional agent Invited International conference
Koichi Moriyama
The 2nd Osaka University — De La Salle University Workshop on Empathic Computing 2010.09
Event date： 2010.09
Language：English Presentation type：Oral presentation (invited, special)
Venue：Manila Country：Philippines
Awards
-
2019年度人工知能学会全国大会（第33回）優秀賞
2019.06 人工知能学会 非負値多重行列因子分解の因子行列を用いたクラスタリングと決定木学習によるオフィスの入退室データの分析
小島世大, 石槫隼人, 坂田美和, 武藤敦子, 森山甲一, 犬塚信博
Award type：Award from Japanese society, conference, symposium, etc. Country：Japan
-
Best Student Paper
2016.02 The 8th International Conference on Agents and Artificial Intelligence (ICAART) Adaptive Two-stage Learning Algorithm for Repeated Games
Wataru Fujita, Koichi Moriyama, Ken-ichi Fukui, Masayuki Numao
Award type：Award from international society, conference, symposium, etc. Country：Italy
-
Best 6 Papers
2007.12 The 27th SGAI International Conference on Artificial Intelligence Modelling Affective-based Music Compositional Intelligence with the Aid of ANS Analyses
Toshihito Sugimoto, Roberto Legaspi, Akihiro Ota, Koichi Moriyama, Satoshi Kurihara, Masayuki Numao
Award type：Award from international society, conference, symposium, etc. Country：United Kingdom
Scientific Research Funds Acquisition Results
-
連続の意思決定を要する環境における報酬評価システムの進化
2019.04 - 2024.03
科学研究費補助金 基盤研究(C)
森山甲一
Authorship：Principal investigator
-
仮想社会における強化学習エージェントの報酬評価システム発現過程の解析
2016.04 - 2019.03
科学研究費補助金 基盤研究(C)
森山甲一
Authorship：Principal investigator
-
エージェントの学習における適切な効用の導出方法
2006.04 - 2009.03
科学研究費補助金 若手研究(B)
森山甲一
Authorship：Principal investigator
-
効率性・頑健性と公平性を両立するフィジカルインターネットのメカニズム設計
2024.04 - 2028.03
科学研究費補助金 基盤研究(B)
櫻井祐子
Authorship：Coinvestigator(s)
-
人工社会アプローチによる賑わい空間マネジメントのシミュレーション科学
2018.04 - 2023.03
科学研究費補助金 基盤研究(A)
兼田敏之
Authorship：Coinvestigator(s)
Other External Funds
-
GPGPUを用いたマルチエージェント強化学習シミュレーションの研究
2016.04 - 2018.03
民間財団等 第25回 堀科学芸術振興財団 第2部研究助成
森山甲一
Authorship：Principal investigator Grant type：Competitive
-
マルチエージェント環境における「感情」に基づく社会的エージェントの構築
2016.01 - 2017.12
民間財団等 栢森情報科学振興財団 第20回助成事業
森山甲一
Authorship：Principal investigator Grant type：Competitive
Committee Memberships
-
International Conference on Principles and Practice of Multi-Agent Systems (PRIMA) Tutorial Chair
2024
Committee type：Other
-
人工知能学会 代議員
2023.06
Committee type：Academic society
-
International Conference on Agents and Artificial Intellligence (ICAART) PC Member
2023
Committee type：Other
-
Joint Agent Workshop and Symposium Executive Committee Member
2023
Committee type：Other
-
International Joint Conference on Aritificial Intelligence (IJCAI) Local Arrangement Committee Member
2020
Committee type：Other
-
International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS) PC Member
2019
Committee type：Other
-
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) PC Member
2019
Committee type：Other
-
IEEE International Conference on Agents (ICA) Publicity Co-chair
2018
Committee type：Other
-
International Conference on Principles and Practice of Multi-Agent Systems (PRIMA) Publicity Co-chair
2018
Committee type：Other
-
Joint Agent Workshop and Symposium Executive Committee Chair
2017
Committee type：Other