1996 Fiscal Year Annual Research Report

創発的適応・学習に関する理論とその応用

Research Project

Project/Area Number	07243101
Research Institution	Hokkaido University
Principal Investigator	嘉数侑昇北海道大学, 工学部, 教授 (60042090)
Co-Investigator(Kenkyū-buntansha)	畝身達夫創価大学, 工学部, 助教授 (50151915) 古川正志旭川工業高等専門学校, 助教授 (70042091) 小野典彦徳島大学, 工学部, 助教授 (60194594) 石田亨京都大学, 工学部, 教授 (20252489) 三上貞芳北海道大学, 工学部, 助教授 (50229655)
Keywords	強化学習 / 適応 / 創発機能 / 進化 / ソフトコンピューティング / 人工生命 / 知能ロボット / 群知能
Research Abstract	本研究は、工学的立場から,生態系における柔軟性をもつ自律機能発現を双発的適応・学習としてとらえ,そのアナロジーの理論的展開を図り実際にそれらのメカニズムおよびプロセスを構築し,具体的応用を通じて人工システムデザインへの指針を得ることを目標としたものであり,当該期間に得られた成果の概要は以下のようにまとめられる. 1.場モデルによる状態表現の共有手法により複数エージェント全体を強化学習させる理論手法を提案した. 2.リアルタイムサーチ手法であるLRTA9*アルゴリズムの収束安定性の改善するδサーチおよびεサーチ理論を提案し,同時に探索と利用のバランス問題への解決の一つを提案した. 3.複数の学習エージェントが全体として目的の作業を達成するような,エージェントのソフトウエアの進化学習を遺伝的アルゴリズムにより構築する手法を提案した. 4.従来離散的な状態・行動を対象とした強化学習を連続状態・マルチエージェントへ適応するための理論をCMAなどの一般化技法との融合により開発した. 5.FMSの応用として大規模AGV動的スケジューリング問題への強化学習の適用法を導出し,状態空間の圧縮が本質的であることを示してフィルタ技法による圧縮が効果的なことを示した. 6.従来本質的に獲得困難性が伴う動的・カオティックな環境に対する強化学習を,ダイナミックスの再構成による非線型予測手法との組み合わせにより実現する理論を開発した.

Research Products

(91 results)

All Other

All Publications (91 results)

[Publications] Kenichi Matsuura: "Acquiring Objective Function in Distributed Rule-Based Systems from Examcles" Journal of Robotics and Mechatronics. 8・5. 454-458 (1996)
[Publications] 松浦賢一: "クラシファイアシステムにおける組織的ルール形成法の構築" 機械学会論文集. 62・601. 179-186 (1996)
[Publications] Wenwei Yu: "A Study on State GroupingendOpportunity Evalutation for Reinforcement Learning Methods" IntelligentEngineering Systems Through Artificail Neural Networks. 6・. (1996)
[Publications] Shinichiro Yoshii: "Atomoid A New Prospect in Reaction-Formation System" Artificial V (Alife V). 383-390 (1996)
[Publications] Hidenori Sakanashi: "Genetic Approach for Autonomous Learning and Structual Evolution" 3rd International Symposium on Distributed Autonomous Robotio Systems. (1996)
[Publications] N. Hondo: "Robust GP in Robot Learning" Parallel Problem Solving from Nature. 751-760 (1996)
[Publications] Hidenori Sakanashi: "An Approach for Genetic Synthesizer of Binary Decision Diagram" 1996 IEEEInternational Conference on Evolutionary Computing. (1996)
[Publications] Hidenori Sakanashi: "Evolution of Binary Decition Diagrams Diagrams for Digtal Circuit Design using Genetic Programming" Proceedings of the First International Conference on Evolvable Systems. (1996)
[Publications] Wenwei Yu: "State Grouping and Opportunity Evaluation for Reinforcement Learning Methods-An Preliminary study for Learning Field Model for Multi-Agent System" Workshop Learning Interactionand Organizations in Mutiagent. 1-8 (1996)
[Publications] Wenwei Yu: "A Study on Opprtunity Evaluation for Reinforcement Learning Methods" Proceedings of the JAPAN-USA Symposiumon Flexible Automation 1996. 2・. 1553-1559 (1996)
[Publications] N. Hondo: "Sharing and Refinement for Reusable Subroutines of Genetic Programming" Inter Conf. on Evolutionay Computation (ICEC'96). 565-570 (1996)
[Publications] N. Hondo: "An Approach to Robustness and Reusability in Genetic Programming" Genetic Programming 96. 429- (1996)
[Publications] Jun Hakura: "An Approach to Realizationof Affordance like Cognitive Mechanism" Proc. of An International Workshop onLearning for Autonomous Robots (ROBOLEARN-96). 28-37 (1996)
[Publications] T. Ishida: "Improving the Learning Effciencies of Realtime Search" Proc. National Conference on Artificial Intelligence (AAAI-96). 305-310 (1996)
[Publications] H. Ishiguro: "Robot Oriented state space construction" Proc. Int. Conf. Intelligent Robots and Systems (IROS-96). 1496-1501 (1996)
[Publications] 畝見達夫: "ヒューマンロボットシステムと人工生命" 第1回JSMEロボメカ・カンボジア. 181-184 (1996)
[Publications] 畝見達夫: "実例に基づくQ学習" 第12回ファジィシステムシンポジウム. 887-890 (1996)
[Publications] 畝見達夫: "行動の創発的学習と進化" 第35回計測自動制御学会学術講演会. (1996)
[Publications] 畝見達夫: "強化学習エージェント集団の進化" 第2回創発システムシンポジウム. 42-47 (1996)
[Publications] 永吉正浩: "進化するロボット群の生活史について" 計測自動制御学会システム・情報合同シンポジウム. 87-92 (1996)
[Publications] 畝見達夫: "A LIFE" 知能工学概論. 133-148 (1996)
[Publications] Tatsuo Unemi: "Evolution of Reionforcement Learning Agents--toward a feasible design of evolvable robot team" ICMAS 96 Workshop on learning interactions and organizations inmultiagent environment. (1996)
[Publications] 畝見達夫: "進化ロボット群についての種文化分析" 第9回自律分散システムシンポジウム. 135-140 (1996)
[Publications] A. T. Rahmani: "A Genetic Algorithm for the Two-Dimensional General Guillotine Cutting Problem" Chinese Jounal of Advanced Software Research : 3 : 1. 66・70. (1996)
[Publications] A. T. Rahmani: "Constrained Optimization with Genetic Algorithms" 人工知能学会誌. 11・3. 113-121 (1996)
[Publications] N. Ono: "Synthesis of Herding and Specialized Behavior by Modular Q-learning Animats" Artificial Life V. 26-30 (1996)
[Publications] N. Ono: "Collective Behavior by Modular Reinforcement-Learning Animats" From Animals to Aniomats 4. 618-624 (1996)
[Publications] N. Ono: "Synthesizing Collective Intelligence" A Modular Reinforcement Learning Approach. Proceedings of the 3rd France. 416-420 (1996)
[Publications] N. Ono: "Reiinforcement Learning Approach to the Multi-agent Block-Pushing Problem" Proceedings of the 3rd France-Japan Congress & 1stEurope-Asia Congress on Mechatronics. 421-425 (1996)
[Publications] N. Ono: "A Genetic Approach to the Generic Crew Scheduing Problem" EXPERSYS-96 : Expert Systems Applications & Artificial Intelligence. 279-284 (1996)
[Publications] N. Ono: "Acquisition of Optimal Communication by Episode-Sharing Artifical Organisms" EXPERSYS-96 : Expert Systems Applications & Artificial Intelligence. 285-290 (1996)
[Publications] N. Ono: "Multiagent Reinforcement Learning in a Continuous Enviroment" EXPERSYS-96 : Expert Systems Applications $&Artificial Intelligence. 291-296 (1996)
[Publications] N. Ono: "Learning to Coordinate : A Reinforcement Learning Approach" EPERSYS-96 : Expert Systems Applications & Artificial Intelligence. 297-302 (1996)
[Publications] N. Ono: "Acquisition of Coordinated Behavior by Modular Q-learning Agents" Proceedings of IEEE/RSJ InternationalConference on Intelligent Robots and Systems. 1525-1529 (1996)
[Publications] N. Ono: "Multi-agent Reinforcement Learning A Modular Approach" Proceedings of the Second International Conference on Multiagent Systems. 252-258 (1996)
[Publications] N. Ono: "A Modular Approach to Multiagent Reinforcemen tLearning" ICMA'96 Wokshop Notes on Learning, Interactions and Organizations in Multiagent Environment. (1996)
[Publications] N. Ono: "Learning to Coordinate in a Continuous Enviroment" JCMAS'96 Workshop Notes on Learning, Interactions and Organizations in Multiagent Environment. (1996)
[Publications] 古川正志: "確率的学習オートマトンによる複数AGVの自律的走行" 精密工学誌. 62・2. 260-264 (1996)
[Publications] 古川正志: "一方向走行レーンをもつFMS工場における複数AGVの運行スケジューリング(遺伝的アルゴリズムによる調和スケジューリング)" 日本機械学会論文集. 62・595. 407-412 (1996)
[Publications] Masashi Furukawa: "COOPERATED WORKS OFDIGITAL BUGS CAPABLE OF TERRITORIAL RECOGNITON" 1996 JAPAN-USA SYSMPOSIUM ONFLEXIBLE AUTOMATION. 1485-1488 (1996)
[Publications] Masashi Furukawa: "APPLICATION OF APPLICATION OF REINFORCEMENT LEARNING TO DISRIBUTED AUTONOMOUS PRODUCTIONSYSTEM-AUTONOMOUS SCHEDULING OF" Adaptive Distributed Parallel Computing Symposium. 436-445 (1996)
[Publications] M. Furukawa: "EVOLUTIONARY COMPUTATION APPLIEDTO THE LOGISTIC CIM SYSTEM" INTERNATIONAL CONFERENCE ON ADVANCES INPRODUCTION MANAGEMANT SYSTEM (APMS'96). 319-324 (1996)
[Publications] 古川正志: "一方向走行レーン上のAGV走行スケジューリング" 第8回自律分散システムシンポジウム資料. 95-100 (1996)
[Publications] 古川正志: "なわばりを認識する群ロボットの協調動作" 1996年度精密工学会春期大会学術講演会講演論文集. 87-88 (1996)
[Publications] 渡辺美和子: "実数型による自動倉庫の在庫割り当ての最適化" 1996年度精密工学会春期大会学術講演会講演論文集. 455-456 (1996)
[Publications] 古川正志: "進化計算の自動倉庫のスケジューラへの組み込みとその実際" 日本機械学会第73期通常総会講演会. 45-46 (1996)
[Publications] 古川正志: "デジタルバグの社会性の実験" 第12回ファジィシステムシンポジウム講演論文集. 795-798 (1996)
[Publications] 古川正志: "縄張り意識によるデジタルバグの群協調行動" 日本機械学会ロボティクス・メカトルニクス講演会'96. 933-936 (1996)
[Publications] 平井幸基: "強化学習における状態圧縮の研究-AGV自律走行問題の事例-" 1996年度精密工学会北海道支部学術講演会講演論文集. 121-122 (1996)
[Publications] 土門邦恭: "強化学習を行う管理エージェントによる流通CIMスケジューラの基礎研究" 1996年度精密工学会北海道支部学術講演会講演論文集. 31-32 (1996)
[Publications] 西浦正規: "流通CIM設計シュミレータの開発" 1996年度精密工学会北海道支部学術講演会講演論文集. 41-42 (1996)
[Publications] 渡辺美和子: "GAによる自動倉庫スケジューラの開発-強化学習によるウェイトの調整-" 1996年度精密工学会北海道支部学術講演会講演論文集. 45-46 (1996)
[Publications] Tomoyoshi Nakayama: "A Realization of Socially Adaptive Robots by Competitive Reinforcement Learning" 5th IEEE International Workshop on Robot and Humen Communicatior. 107-111 (1996)
[Publications] Sadayoshi Mikami: "Combining Reinforcement Learning with GA to Co-ordinated Control Rules for Multi-Agent System" 1996 IEEE International Conference on Evolutionary Computation. 231-236 (1996)
[Publications] Sadayoshi Mikami: "Acquiring Co-operation without Communication by Reinforcemenyt Learning Dynamics Identification" Distributed Autonomous Robotic Systems 2. 439-439 (1996)
[Publications] Mitsuo Wada: "An Approach to Chaos and Self-Organizing Behaviors in Symbiotic Relationsips between Human and Robots" Journal of Robotics and Mechatronics. 8・4. 318-322 (1996)
[Publications] 三上貞芳: "創発システム研究がめざすもの" 計測と制御. 35・7. 557-563 (1996)
[Publications] Fei Qian: "A Parallel Learning Celluler Automata for Combinatorial Optimization Problems" Proc. of ICEC'96 (NAGOYA). 553-558 (1996)
[Publications] Fei Qian: "A Consideration of Learning Cellular Automata with The Global Self-Improving Behavior" Preprints of the 28th ISCIE Internationl Symposium on Stochastic Systems Theory and Its Applications. 33-34 (1996)
[Publications] Kiyohiko Nakamura: "Latency competition as cortical processing of millisecond time scale" Proc. World Congress on Neural Networks. 1291-1294 (1996)
[Publications] Kiyohiko Nakamura: "Neural Mechanism of latency competition for cortical processing of subsecond time range" Society for Neuroscience Abstracts. 22・3. 1936- (1996)
[Publications] Kiyohiko Nakamura: "A model of ventral pathway of temporal lobereproducing neural responses of superior temporal sulcus" Neuroscience Research. Suppl 20・ S266. (1996)
[Publications] Kiyohiko Nakamura: "Evidence for latency competition producing sub-second response of the cerebrum." Dynamical Neuroscience Symposium Abstracts. 4- (1996)
[Publications] 中村清彦: "発火潜時競争機構のサル側頭葉細胞応答による検証" 電子情報通信学会技術研究報告. NC95・599. 209-214 (1996)
[Publications] 中村清彦: "大脳皮質におけるミリ秒時間域の情報処理機構-サル側頭葉の神経細胞活動の解析" 東京工業大学脳研究シンポジウム講演抄録集. 19-24 (1996)
[Publications] 浅田稔: "視覚と行動の密な統合を目指すロボットビジョン" 光学. 25・5. 252-257 (1996)
[Publications] 浅田稔: "特集ロボカップ,3,ロボットプレーヤの感覚と学習" bit. 28・5. 37-43 (1996)
[Publications] M. Asada: "Behavior Acquisition viaVision-Based Robot Learning" Robotics Research. 279-286 (1996)
[Publications] 浅田稔: "新しいAl研究目指して分担執筆第7章「主体と環境」-身体性に関する一考察-" 人工知能学会誌. 11・5. 721-723 (1996)
[Publications] M. Asada: "Purposive Behavior Acquisition for a Real Robot by Vision-Based ReinforcementLearning" Mechine Learning. 23・5. 279-303 (1996)
[Publications] 浅田稔: "ロボットの行動学習" 日本機械学会論文集C編. 62・602. 3746-3751 (1996)
[Publications] 内部英治: "競合エージェントの存在する環境での視覚に基づく強化学習によるロボットの行動獲得" 第8回自律分散システム・シンポジウム資料. 371-374 (1996)
[Publications] M. Asada: "Target Reaching Behavior Learning with Occlision Detection and Avcidance for A Stereo Vision-Based Mobile Robot" Proc. of ROBOLEARN96 : An International Workshop on Learning for Autonomous Robots. 1-10 (1996)
[Publications] K. Nakamura: "Stereo Sketch : Stereo Vision-Based Target Reaching Behavior Acquisition with Occlusion Detection and Avoidance" Proc. of IEEE int. Conf. on Robotics and Automation. 1314-1319 (1996)
[Publications] 内部英治: "サッカーロボットの技能学習" つくばソフトウェアシンポジウム予稿集. 43-46 (1996)
[Publications] 浅田稔: "サッカーロボットにおける振舞の認識と行動" 第1回JSMEロボメカ・シンポジア--ヒューマン・ロボット・シンポジア. 146-149 (1996)
[Publications] 高橋: "状態空間の自律的分割による実ロボットの実時間学習" ロボディクス・メカトロニクス講演会96予稿集. 121-124 (1996)
[Publications] M. Asada: "Action-Based Sensor Space Categorization for Robot Learning" Proc. of IEEE/RSJ/Gl InternationalConference on Intelligent Robots and Systems 1996 (IROS'96). 1502-1509 (1996)
[Publications] Eiji Uchibe: "Behavior Coordination for a Mobile Robot Using Modular Reinforcement Learning" Proc. of IEEE/RSJ/Gllnternational Conference on Intelligent Robots and Systems 1996 (IROS'96). 1329-1336 (1996)
[Publications] Yasutake Takahashi: "ReasonablePerformance in Less Learning Time by Real Robot Based on Incremental StateSpace Segmentation" Proc. of IEEE/RSJ/Gl international Conference on Intelligent Robots and Systems 1996 (IROS'96). 1518-1524 (1996)
[Publications] Eiji Uchibe: "Vision-Based Reinforcement Learning for RoboCup" Towards RealRobot Competition, Proceedings of IROS-96 Workshop on RoboCup. 19-24 (1996)
[Publications] Minoru Asada: "An Agent and an Environment : A View on "Having Bodies"-A Case Study on Behavior Learning for Vision-Based Mobile Robot-" Proceedings of 1996 IROS Workshop on Towards Real Autonomy. 19-24 (1996)
[Publications] Yasutake Takahashi: "Sensor Space Segmentation for Moble Robot Learning" Proceedings of ICMAS'96 Workshop on Learning. (1996)
[Publications] Eiji Uchibe: "Strategy Classification in Multi-agent Env. ronment-Applying Reinforcement Learning to Soccer Agantes-" Proceedings of ICMAS'96 Workshop on RoboCup workshop. (1996)
[Publications] 浅田稔: "「主体と環境:身体性に関する一考察」-視覚移動ロボットにおける行動学習を例に-" 第2回創発システム・シンポジウム講演資料集. 48-53 (1996)
[Publications] 山田誠二: "動的環境における成功確率を用いた熟考の制御" 人工知能学会誌. 11・4. 645-652 (1996)
[Publications] 山田誠二: "単純タイルワールドにおけるSIPの実験的評価" 人工知能学会誌. 11・5. 744-751 (1996)
[Publications] 山田誠次: "観測行動を伴う仮説推論のためのコスト・効用・信頼度による仮説選好" 人工知能学会誌. 11・5. 795-798 (1996)
[Publications] Yamada. S: "Controlling Deliberation with the Success Probability in a Dynamic Environment" The Third International Conference onArtificial Intelligence Planning Systems (ALPS-96). 251-258 (1996)
[Publications] Yamada. S.: "Applying Self-Organizing Networks to Recognizing Rooms with Behavior Sequences of a Mobile Robot" The International Conference on Neural Networks (ICNN'96). 1790-0794 (1996)
[Publications] Kawaishi. I.: "Experimental Comparison of a Heterogeneous Learning Multi-Agent System with a Homogeneous one" 1996 IEEE International Conference on Systems, Man and Cybernetics (IEEE-SMC-96). 613-618 (1996)

1996 Fiscal Year Annual Research Report

創発的適応・学習に関する理論とその応用

Principal Investigator

嘉数 侑昇 北海道大学, 工学部, 教授 (60042090)

Research Products

[Publications] Kenichi Matsuura: "Acquiring Objective Function in Distributed Rule-Based Systems from Examcles" Journal of Robotics and Mechatronics. 8・5. 454-458 (1996)

[Publications] 松浦賢一: "クラシファイアシステムにおける組織的ルール形成法の構築" 機械学会論文集. 62・601. 179-186 (1996)

[Publications] Wenwei Yu: "A Study on State GroupingendOpportunity Evalutation for Reinforcement Learning Methods" IntelligentEngineering Systems Through Artificail Neural Networks. 6・. (1996)

[Publications] Shinichiro Yoshii: "Atomoid A New Prospect in Reaction-Formation System" Artificial V (Alife V). 383-390 (1996)

[Publications] Hidenori Sakanashi: "Genetic Approach for Autonomous Learning and Structual Evolution" 3rd International Symposium on Distributed Autonomous Robotio Systems. (1996)

[Publications] N. Hondo: "Robust GP in Robot Learning" Parallel Problem Solving from Nature. 751-760 (1996)

[Publications] Hidenori Sakanashi: "An Approach for Genetic Synthesizer of Binary Decision Diagram" 1996 IEEEInternational Conference on Evolutionary Computing. (1996)

[Publications] Hidenori Sakanashi: "Evolution of Binary Decition Diagrams Diagrams for Digtal Circuit Design using Genetic Programming" Proceedings of the First International Conference on Evolvable Systems. (1996)

[Publications] Wenwei Yu: "State Grouping and Opportunity Evaluation for Reinforcement Learning Methods-An Preliminary study for Learning Field Model for Multi-Agent System" Workshop Learning Interactionand Organizations in Mutiagent. 1-8 (1996)

[Publications] Wenwei Yu: "A Study on Opprtunity Evaluation for Reinforcement Learning Methods" Proceedings of the JAPAN-USA Symposiumon Flexible Automation 1996. 2・. 1553-1559 (1996)

[Publications] N. Hondo: "Sharing and Refinement for Reusable Subroutines of Genetic Programming" Inter Conf. on Evolutionay Computation (ICEC'96). 565-570 (1996)

[Publications] N. Hondo: "An Approach to Robustness and Reusability in Genetic Programming" Genetic Programming 96. 429- (1996)

[Publications] Jun Hakura: "An Approach to Realizationof Affordance like Cognitive Mechanism" Proc. of An International Workshop onLearning for Autonomous Robots (ROBOLEARN-96). 28-37 (1996)

[Publications] T. Ishida: "Improving the Learning Effciencies of Realtime Search" Proc. National Conference on Artificial Intelligence (AAAI-96). 305-310 (1996)

[Publications] H. Ishiguro: "Robot Oriented state space construction" Proc. Int. Conf. Intelligent Robots and Systems (IROS-96). 1496-1501 (1996)

[Publications] 畝見達夫: "ヒューマンロボットシステムと人工生命" 第1回JSMEロボメカ・カンボジア. 181-184 (1996)

[Publications] 畝見達夫: "実例に基づくQ学習" 第12回ファジィシステムシンポジウム. 887-890 (1996)

[Publications] 畝見達夫: "行動の創発的学習と進化" 第35回計測自動制御学会学術講演会. (1996)

[Publications] 畝見達夫: "強化学習エージェント集団の進化" 第2回創発システムシンポジウム. 42-47 (1996)

[Publications] 永吉正浩: "進化するロボット群の生活史について" 計測自動制御学会システム・情報合同シンポジウム. 87-92 (1996)

[Publications] 畝見達夫: "A LIFE" 知能工学概論. 133-148 (1996)

[Publications] Tatsuo Unemi: "Evolution of Reionforcement Learning Agents--toward a feasible design of evolvable robot team" ICMAS 96 Workshop on learning interactions and organizations inmultiagent environment. (1996)

[Publications] 畝見達夫: "進化ロボット群についての種文化分析" 第9回自律分散システムシンポジウム. 135-140 (1996)

[Publications] A. T. Rahmani: "A Genetic Algorithm for the Two-Dimensional General Guillotine Cutting Problem" Chinese Jounal of Advanced Software Research : 3 : 1. 66・70. (1996)

[Publications] A. T. Rahmani: "Constrained Optimization with Genetic Algorithms" 人工知能学会誌. 11・3. 113-121 (1996)

[Publications] N. Ono: "Synthesis of Herding and Specialized Behavior by Modular Q-learning Animats" Artificial Life V. 26-30 (1996)

[Publications] N. Ono: "Collective Behavior by Modular Reinforcement-Learning Animats" From Animals to Aniomats 4. 618-624 (1996)

[Publications] N. Ono: "Synthesizing Collective Intelligence" A Modular Reinforcement Learning Approach. Proceedings of the 3rd France. 416-420 (1996)

[Publications] N. Ono: "Reiinforcement Learning Approach to the Multi-agent Block-Pushing Problem" Proceedings of the 3rd France-Japan Congress & 1stEurope-Asia Congress on Mechatronics. 421-425 (1996)

[Publications] N. Ono: "A Genetic Approach to the Generic Crew Scheduing Problem" EXPERSYS-96 : Expert Systems Applications & Artificial Intelligence. 279-284 (1996)

[Publications] N. Ono: "Acquisition of Optimal Communication by Episode-Sharing Artifical Organisms" EXPERSYS-96 : Expert Systems Applications & Artificial Intelligence. 285-290 (1996)

[Publications] N. Ono: "Multiagent Reinforcement Learning in a Continuous Enviroment" EXPERSYS-96 : Expert Systems Applications $&Artificial Intelligence. 291-296 (1996)

[Publications] N. Ono: "Learning to Coordinate : A Reinforcement Learning Approach" EPERSYS-96 : Expert Systems Applications & Artificial Intelligence. 297-302 (1996)

[Publications] N. Ono: "Acquisition of Coordinated Behavior by Modular Q-learning Agents" Proceedings of IEEE/RSJ InternationalConference on Intelligent Robots and Systems. 1525-1529 (1996)

[Publications] N. Ono: "Multi-agent Reinforcement Learning A Modular Approach" Proceedings of the Second International Conference on Multiagent Systems. 252-258 (1996)

[Publications] N. Ono: "A Modular Approach to Multiagent Reinforcemen tLearning" ICMA'96 Wokshop Notes on Learning, Interactions and Organizations in Multiagent Environment. (1996)

[Publications] N. Ono: "Learning to Coordinate in a Continuous Enviroment" JCMAS'96 Workshop Notes on Learning, Interactions and Organizations in Multiagent Environment. (1996)

[Publications] 古川正志: "確率的学習オートマトンによる複数AGVの自律的走行" 精密工学誌. 62・2. 260-264 (1996)

[Publications] 古川正志: "一方向走行レーンをもつFMS工場における複数AGVの運行スケジューリング(遺伝的アルゴリズムによる調和スケジューリング)" 日本機械学会論文集. 62・595. 407-412 (1996)

[Publications] Masashi Furukawa: "COOPERATED WORKS OFDIGITAL BUGS CAPABLE OF TERRITORIAL RECOGNITON" 1996 JAPAN-USA SYSMPOSIUM ONFLEXIBLE AUTOMATION. 1485-1488 (1996)

[Publications] Masashi Furukawa: "APPLICATION OF APPLICATION OF REINFORCEMENT LEARNING TO DISRIBUTED AUTONOMOUS PRODUCTIONSYSTEM-AUTONOMOUS SCHEDULING OF" Adaptive Distributed Parallel Computing Symposium. 436-445 (1996)

[Publications] M. Furukawa: "EVOLUTIONARY COMPUTATION APPLIEDTO THE LOGISTIC CIM SYSTEM" INTERNATIONAL CONFERENCE ON ADVANCES INPRODUCTION MANAGEMANT SYSTEM (APMS'96). 319-324 (1996)

[Publications] 古川正志: "一方向走行レーン上のAGV走行スケジューリング" 第8回自律分散システムシンポジウム資料. 95-100 (1996)

[Publications] 古川正志: "なわばりを認識する群ロボットの協調動作" 1996年度精密工学会春期大会学術講演会講演論文集. 87-88 (1996)

[Publications] 渡辺美和子: "実数型による自動倉庫の在庫割り当ての最適化" 1996年度精密工学会春期大会学術講演会講演論文集. 455-456 (1996)

[Publications] 古川正志: "進化計算の自動倉庫のスケジューラへの組み込みとその実際" 日本機械学会第73期通常総会講演会. 45-46 (1996)

[Publications] 古川正志: "デジタルバグの社会性の実験" 第12回ファジィシステムシンポジウム講演論文集. 795-798 (1996)

[Publications] 古川正志: "縄張り意識によるデジタルバグの群協調行動" 日本機械学会ロボティクス・メカトルニクス講演会'96. 933-936 (1996)

[Publications] 平井幸基: "強化学習における状態圧縮の研究-AGV自律走行問題の事例-" 1996年度精密工学会北海道支部学術講演会講演論文集. 121-122 (1996)

[Publications] 土門邦恭: "強化学習を行う管理エージェントによる流通CIMスケジューラの基礎研究" 1996年度精密工学会北海道支部学術講演会講演論文集. 31-32 (1996)

[Publications] 西浦正規: "流通CIM設計シュミレータの開発" 1996年度精密工学会北海道支部学術講演会講演論文集. 41-42 (1996)

[Publications] 渡辺美和子: "GAによる自動倉庫スケジューラの開発-強化学習によるウェイトの調整-" 1996年度精密工学会北海道支部学術講演会講演論文集. 45-46 (1996)

[Publications] Tomoyoshi Nakayama: "A Realization of Socially Adaptive Robots by Competitive Reinforcement Learning" 5th IEEE International Workshop on Robot and Humen Communicatior. 107-111 (1996)

[Publications] Sadayoshi Mikami: "Combining Reinforcement Learning with GA to Co-ordinated Control Rules for Multi-Agent System" 1996 IEEE International Conference on Evolutionary Computation. 231-236 (1996)

[Publications] Sadayoshi Mikami: "Acquiring Co-operation without Communication by Reinforcemenyt Learning Dynamics Identification" Distributed Autonomous Robotic Systems 2. 439-439 (1996)

[Publications] Mitsuo Wada: "An Approach to Chaos and Self-Organizing Behaviors in Symbiotic Relationsips between Human and Robots" Journal of Robotics and Mechatronics. 8・4. 318-322 (1996)

[Publications] 三上貞芳: "創発システム研究がめざすもの" 計測と制御. 35・7. 557-563 (1996)

[Publications] Fei Qian: "A Parallel Learning Celluler Automata for Combinatorial Optimization Problems" Proc. of ICEC'96 (NAGOYA). 553-558 (1996)

[Publications] Fei Qian: "A Consideration of Learning Cellular Automata with The Global Self-Improving Behavior" Preprints of the 28th ISCIE Internationl Symposium on Stochastic Systems Theory and Its Applications. 33-34 (1996)

[Publications] Kiyohiko Nakamura: "Latency competition as cortical processing of millisecond time scale" Proc. World Congress on Neural Networks. 1291-1294 (1996)

[Publications] Kiyohiko Nakamura: "Neural Mechanism of latency competition for cortical processing of subsecond time range" Society for Neuroscience Abstracts. 22・3. 1936- (1996)

[Publications] Kiyohiko Nakamura: "A model of ventral pathway of temporal lobereproducing neural responses of superior temporal sulcus" Neuroscience Research. Suppl 20・ S266. (1996)

[Publications] Kiyohiko Nakamura: "Evidence for latency competition producing sub-second response of the cerebrum." Dynamical Neuroscience Symposium Abstracts. 4- (1996)

[Publications] 中村清彦: "発火潜時競争機構のサル側頭葉細胞応答による検証" 電子情報通信学会技術研究報告. NC95・599. 209-214 (1996)

[Publications] 中村清彦: "大脳皮質におけるミリ秒時間域の情報処理機構-サル側頭葉の神経細胞活動の解析" 東京工業大学脳研究シンポジウム講演抄録集. 19-24 (1996)

[Publications] 浅田稔: "視覚と行動の密な統合を目指すロボットビジョン" 光学. 25・5. 252-257 (1996)

[Publications] 浅田稔: "特集ロボカップ,3,ロボットプレーヤの感覚と学習" bit. 28・5. 37-43 (1996)

[Publications] M. Asada: "Behavior Acquisition viaVision-Based Robot Learning" Robotics Research. 279-286 (1996)

[Publications] 浅田稔: "新しいAl研究目指して分担執筆第7章「主体と環境」-身体性に関する一考察-" 人工知能学会誌. 11・5. 721-723 (1996)

[Publications] M. Asada: "Purposive Behavior Acquisition for a Real Robot by Vision-Based ReinforcementLearning" Mechine Learning. 23・5. 279-303 (1996)

[Publications] 浅田稔: "ロボットの行動学習" 日本機械学会論文集C編. 62・602. 3746-3751 (1996)

[Publications] 内部英治: "競合エージェントの存在する環境での視覚に基づく強化学習によるロボットの行動獲得" 第8回自律分散システム・シンポジウム資料. 371-374 (1996)

[Publications] M. Asada: "Target Reaching Behavior Learning with Occlision Detection and Avcidance for A Stereo Vision-Based Mobile Robot" Proc. of ROBOLEARN96 : An International Workshop on Learning for Autonomous Robots. 1-10 (1996)

[Publications] K. Nakamura: "Stereo Sketch : Stereo Vision-Based Target Reaching Behavior Acquisition with Occlusion Detection and Avoidance" Proc. of IEEE int. Conf. on Robotics and Automation. 1314-1319 (1996)

[Publications] 内部英治: "サッカーロボットの技能学習" つくばソフトウェアシンポジウム予稿集. 43-46 (1996)

嘉数侑昇北海道大学, 工学部, 教授 (60042090)