Papers - MATSUI Toshihiro
-
Applying Reward Design Based on Payment Mechanism to Shaped-Reward DQN for Beer Game Reviewed
Masaaki Hori, Toshihiro Matsui
Proc. 2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)/11th Intl. Conf. on Smart Computing and Artificial Intelligence 384 - 390 2022.09
Authorship:Last author Language:English Publishing type:Research paper (international conference proceedings)
-
Anytime Evolutionary DCOP Algorithm with Distributed Solution Stores Reviewed
Toshihiro Matsui
Proc. of 16th International KES Conference on Agents and Multi-Agent Systems Technologies and Applications (KES-AMSTA-22) 61 - 76 2022.08
Authorship:Lead author Language:English Publishing type:Research paper (international conference proceedings)
-
Negotiation Considering Privacy Loss on Asymmetric Multi-objective Decentralized Constraint Optimization Problem Reviewed
Toshihiro Matsui
Agents and Artificial Intelligence, 13th Intl. Conf. on Agents and Artificial Intelligence, Revised Selected Papers, LNAI 13251 85 - 110 2022.07
Authorship:Lead author Language:English Publishing type:Research paper (scientific journal)
-
A Study for Decentralized Cooperative Reinforcement Learning with Fairness Among Agents
Toshihiro Matsui
1N1-GS-5-05 - 1N1-GS-5-05 2022.06
Authorship:Lead author Language:Japanese Publishing type:Research paper (other academic)
-
Improvement of Task Allocation in TP Algorithm for MAPD Problem by Relaxation of Movement Limitation and Estimation of Pickup Time Reviewed
Masanori Shimokawa, Toshihiro Matsui
Transactions of the Japanese Society for Artificial Intelligence 37 ( 3 ) A-L84_1 - 13 2022.05
Authorship:Last author Language:Japanese Publishing type:Research paper (scientific journal)
DOI: https://doi.org/10.1527/tjsai.37-3_A-L84
DOI: https://doi.org/10.1527/tjsai.37-3_A-L84
Other Link: https://www.jstage.jst.go.jp/article/tjsai/37/3/37_37-3_A-L84/_article/-char/en
-
Study of Extended Multiagent Pickup-and-Delivery Problem for Simultaneous Task Execution Under Capacity Constraints
Masanori Shimokawa, Toshihiro Matsui
120 72 - 77 2022.03
Authorship:Last author Language:Japanese Publishing type:Research paper (conference, symposium, etc.)
-
A Study on Application of Shaped-Reward DQN to Beer Game with Multiple Learning Agents
Masaaki Hori, Toshihiro Matsui
D-8-3 - D-8-3 2022.03
Authorship:Last author Language:Japanese Publishing type:Research paper (other academic)
-
A Study on Evolutionary Algorithm with Decentralized Management of Solution Sets for Distributed Constraint Optimization Problem
Toshihiro Matsui
2 43 - 44 2022.03
Authorship:Lead author Language:Japanese Publishing type:Research paper (other academic)
-
Study on Applying Decentralized Evolutionary Algorithm to Asymmetric Multi-objective DCOPs with Fairness and Worst Case Reviewed International journal
Toshihiro Matsui
Proc. 14th International Conference on Agents and Artificial Intelligence (ICAART 2022) 1 417 - 424 2022.02
Authorship:Lead author Language:English Publishing type:Research paper (international conference proceedings)
Other Link: https://www.scitepress.org/Link.aspx?doi=10.5220/0010919500003116
-
マルチエージェント強化学習の差分報酬近似手法における推定報酬の学習の改良
中嶋 亮太, 松井 俊浩
情報処理学会研究報告 2022-ICS-205 ( 12 ) 2022.02
Authorship:Last author Language:Japanese Publishing type:Research paper (conference, symposium, etc.)
-
A Study on Applying Decentralized Constraint Optimization to Mobile Sensor Teams with Range Sensors Reviewed International journal
Toshihiro Matsui
Proc. 5th International Conference on Advances in Artificial Intelligence (ICAAI 2020) 2021.11
Authorship:Lead author Language:English Publishing type:Research paper (international conference proceedings)
-
距離情報に基づく観測と位置推定のための複数移動センサによる観測タスクへの非集型制約最適化の適用の一検討
松井 俊浩
2021年度人工知能学会全国大会(第35回)論文集 2021.06
Authorship:Lead author Language:Japanese Publishing type:Research paper (conference, symposium, etc.)
-
分散制約最適化のための進化的計算と確率的探索の併用の一検討
岡 大貴, 松井 俊浩
2021年度電子情報通信学会総合大会 情報・システム論文集 1 66 - 66 2021.03
Language:Japanese Publishing type:Research paper (conference, symposium, etc.)
-
在宅勤務と欠勤者を考慮するシフトスケジューリング問題の検討
福田 悠也, 松井 俊浩
2021年度電子情報通信学会総合大会 情報・システム論文集 1 60 - 60 2021.03
Language:Japanese Publishing type:Research paper (conference, symposium, etc.)
-
MAPF問題におけるエージェントの操作回数を考慮する経路探索と退避先頂点の選択手法の検討
宮地 亨輔, 松井 俊浩
2021年度電子情報通信学会総合大会 情報・システム論文集 1 57 - 57 2021.03
Language:Japanese Publishing type:Research paper (conference, symposium, etc.)
-
複数移動センサによる複合的な協調観測のための非集中型制約最適化の検討
松井 俊浩
情報処理学会第83回全国大会講演論文集 2 41 - 42 2021.03
Authorship:Lead author Language:Japanese Publishing type:Research paper (conference, symposium, etc.)
-
Investigation on Stochastic Local Search for Decentralized Asymmetric Multi-objective Constraint Optimization Considering Worst Case Reviewed International journal
Toshihiro Matsui
Proc. 13th International Conference on Agents and Artificial Intelligence (ICAART 2021) 1 462 - 469 2021.02
Authorship:Lead author Language:English Publishing type:Research paper (international conference proceedings)
-
A Study on Negotiation for Revealed Information with Decentralized Asymmetric Multi-objective Constraint Optimization Reviewed International journal
Toshihiro Matsui
Proc. 13th International Conference on Agents and Artificial Intelligence (ICAART 2021) 1 149 - 159 2021.02
Authorship:Lead author Language:English Publishing type:Research paper (international conference proceedings)
-
Decentralized Constraint Optimization in Composite Observation Task Allocation to Mobile Sensor Agents Reviewed International journal
Toshihiro Matsui
Proc. 18th International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS2020) 171 - 187 2020.10
Authorship:Lead author Language:English Publishing type:Research paper (international conference proceedings)
-
MAPD問題における滞在の予約と移動予測時間を用いるタスク割り当て
下川真典,松井俊浩
第19回情報科学技術フォーラム(FIT2020)論文集 2 255 - 262 2020.09
Language:Japanese Publishing type:Research paper (conference, symposium, etc.)