MENU

PUBLICATIONS

Academic Papers | Review and Commentary Articles | Books | Awards | External Funds | Patents

Academic Papers

Journal Paper

  1. Sachiyo Arai, Kanako Suzuki, Encouragement of Right Social Norms by Inverse Reinforcement Learning. Journal of Information Processing, 22(2): pp.299-306, (2014)
  2. Sachiyo Arai, and Tatsuya Masubuchi, A Study of Traffic Flow Optimization by Learning Pace-car : International Journal of Advancements in Computing Technology, 2012; 4(22), pp. 257-268 (2012).
  3. Sachiyo Arai, Yoshihisa Ishigaki, Information Theoretic Approach for Measuring Interaction in Multiagent Domain : Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.13 No.6 Nov.20, pp.649-657, (2009).
  4. Sachiyo Arai, Yoshihisa Ishigaki, Measurement of Underlying Cooperation in Multiagent Reinforcement Learning : Lecture Notes in Computer Science 5357 Springer, pp. 34-41, (2008).
  5. Nobuyuki Tanaka and Sachiyo Arai, Teamwork Formation for Keepaway in Robotics Soccer (Reinforcement Learning Approach) : Lecture Notes in Computer Science, Volume 4088, pp. 279-292, (2006).
  6. Nima Asgharbeygi, Negin Nejati, Pat Langley, Sachiyo Arai, Guiding Inference Through Relational Reinforcement Learning : Lecture Notes in Computer Science, Volume 3625, pp. 20-37, (2005).
  7. Sachiyo Arai, Yohei Murakami, Yuki Sugimoto, Toru Ishida, Semantic Web Service Architecture using Multi-agent Scenario Description: Lecture Notes in Artificial Intelligence, Volume 2891, pp. 98-109, (2003).
  8. Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Controlling Multiple Cranes Using Multi-Agent Reinforcement Learning: Emerging Coordination among Competitive Agents : IEICE Transactions on Communications, Vol.E-83-B, No.5, pp.1039-1047, (2000).

International Conference (more than three reviewers)

  1. Shota Ishikawa, Sachiyo Arai, Cooperative Learning of a Driving Strategy to Suppress Phantom Traffic Jams, IEEE International Conference on Agents, pp.90-93, ISBN: 978-1-5090-3931-9,DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICA.2016.029, (2016. 9.30 Matsue, Japan)
  2. Ryosuke Saitake, Sachiyo Arai, Parameter Estimation of Multi-Objective Reinforcement Learning to Reach Arbitrary Pareto Solution, IEEE International Conference on Agents, pp.110-111, (2016. 9.30 Matsue, Japan)
  3. Sachiyo Arai, Haichi Xu: Faster Convergence to Cooperative Policy by Autonomous Detection of Interference States in Multiagent Reinforcement Learning. PRICAI 2016: 16-29, (2016. 8.22-26, Phuket, Thailand), Lecture Notes in Computer Science Book series (LNCS, volume 9810), pp. 16-29
  4. Shota Ishikawa, Sachiyo Arai, Evaluating Advantage of Sharing Information among Vehicles Toward Avoiding Phantom Traffic Jam, Proceedings of the 2015 Winter Simulation Conference, pp.300-311, (2015.12 USA).
  5. Hino, Y., Arai, S., "Avoid the Overflow of Disaster Victims around the Railway Station -via Adaptive Management of Passengers' Routes and Train Schedule-", RailTokyo2015, 10 pages, (2015.3 Japan).
  6. Sachiyo Arai, and Tatsuya Masubuchi, A Study of Traffic Flow Optimization by Learning Pace-car, The 15th Asia Pacific Symposium on Intelligent and Evolutionary Systems, 6 pages, (2011).
  7. Sachiyo Arai, Yuta Mabuchi, Learning Strategic Information Support for Controlling Traffic Flow, International Conference on Intelligent Unmanned Systems, 6 pages, (2011).
  8. Shuichiro Kanno, and Sachiyo Arai, Interaction Model for Chasm Creation on Multiagent Network, The SICE Annual Conference 2011, 6 pages, (2011).
  9. Yuya Kakui, Sachiyo Arai, Scene Evaluation of a Ball Game for Solving Batting Order Optimization, The SICE Annual Conference 2010, 6 pages, (2010).
  10. Masaki Imajuku, Tatsuya Hiyama, Sachiyo Arai, A Preliminary Analysis of Interactive Effects between Network Structure and Decision Criteria on the Global Behavior, ICROS-SICE International Joint Conference 2009, 6 pages , (2009).
  11. Atsuko Takano, Kazuko Takagi, Sachiyo Arai, Hiroya Takeuchi and Syun Tutiya, CURATOR:its developmental strategy, International Conference on Open Repositories, pp.23-27, (2007).
  12. Nobuyuki Tanaka and Sachiyo Arai, Teamwork Formation for Keepaway in Robotics Soccer, 9th Pacific Rim International Workshop on Multi-Agents, 8 pages, (2006) .
  13. Nobuyuki Tanaka and Sachiyo Arai, Reward Design for Emerging Cooperative Behavior in Continuing Task Domains : International Joint Conference on Autonomous Agents and Multiagent Systems, Workshop on Adaptation and Learning in Autonomous Agents and Multiagent systems, pp. 7-14, (2006).
  14. Nima Asgharbeygi, Negin Nejati, Pat Langley, Sachiyo Arai, Guiding Inference Through Relational Reinforcement Learning, Inductive Logic Programming , pp. 20-37, (2005).
  15. Pat Langley, Sachiyo Arai, and Daniel Shapiro, Model-Based Learning with Hierarchical Relational Skills : International Conference on Machine Learning Workshop on Relational Reinforcement Learning, pp. 63-68 (2004).
  16. Sachiyo Arai and Toru Ishida, Learning for Human-Agent Collaboration on the Semantic Web: International Conference on Informatics Research for Development of Knowledge Society Infrastructure , pp. 132-139, (2004).
  17. Sachiyo Arai, Yohei Murakami, Yuki Sugimoto and Toru Ishida, Multi-agent Scenarios Introducing Semantics for Web Services, The New Trends on Knowledge Processing -Data Mining, Semantic Web and Computational Science 6, Invited Paper, pp. 1-5, (2003).
  18. Sachiyo Arai, Yohei Murakami, Yuki Sugimoto, Toru Ishida, Semantic Web Service Architecture using Multi-agent Scenario Description : 3th Pacific Rim International Conference on Artificial Intelligence, pp.90-109, (2003).
  19. Sachiyo Arai, and Katia Sycara, Credit Assignment Method for Learning Effective Stochastic Policies in Uncertain Domains: GECCO-2001, Proceedings of Genetic and Evolutionary Computation Conference, pp. 815-822, (2001).
  20. Kazuteru Miyazaki, Sachiyo Arai, and Shigenobu Kobayashi, Cranes Control Using Multi-agent Profit Sharing: Proceedings of the 6th International Conference on Information Systems Analysis and Synthesis, pp.178-183, (2000).
  21. Sachiyo Arai, Katia Sycara, and Terry R. Payne, Experience-based Reinforcement Learning to Acquire Effective Behavior in a Multi-agent Domain, Pacific Rim International Conference on Artificial Intelligence, pp.125-135, (2000).
  22. Sachiyo Arai and Katia Sycara, Effective Learning Approach for Planning and Scheduling in Multi-agent Domain : Proceedings of the 6th International Conference on Simulation of Adaptive Behavior (From animals to animats 6), ISAB-2000, pp.507-516, (2000).
  23. Sachiyo Arai and Katia Sycara, Multi-Agent Reinforcement Learning for Planning and Scheduling Multiple Goals, Proceedings of the 4th International Conference on Multi-Agent Systems, pp. 359-360, (2000).
  24. Sachiyo Arai, Shigenobu Kobayashi, Multi-agent Reinforcement Learning for Crane Control Problem : Multi-Agent Reinforcement Learning for Planning and Conflict Resolution in a Dynamic Domain : Designing Rewards for Conflict Resolution, Autonomous Decentralized Systems, pp.310-319 (1999).
  25. Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Cranes Control Using Multi-agent Reinforcement Learning, International Conference on Intelligent Autonomous Systems, Vol.5, pp. 335-342, (1998).
  26. Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Learning Cooperative Behavior by Profit Sharing Agents, Proceedings of the 15th International Joint Conference on Artificial Intelligence, p.7, (1997).
  27. Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Generating Cooperative Behavior by Multi-Agent Reinforcement Learning, Proceedings of the 6th European Workshop on Learning Robots, pp. 111-120, (1997).
  28. Sachiyo Arai, Rational Balancing of Planning and Communication in the Dynamic Multi-agents World: Proceedings of the 4th International Conference on Autonomous Agents, ICMAS-1995, pp.436-437 (1995).
  29. Sachiyo Arai, Masayuki Yamamura, and Shigenobu Kobayashi, Horizontal and Vertical Cooperation by Multi-agents for Dynamic Planning, Proceedings of the 1st Pacific Rim International Conference on Artificial Intelligence, pp.77-82, (1990).
  30. Sachiyo Arai, Masayuki Yamamura, and Shigenobu Kobayashi, Model of Problem Decomposition in Cooperative Planning, Proceedings of the 28th SICE Annual Conference, Vol.2, pp.1255-1258, (1989).

Conference Paper

  1. Nobuyuki Tanaka and Sachiyo Arai, Teamwork Formation for Keepaway in Robotics Soccer (Reinforcement Learning Approach), Ninth Pacific Rim International Workshop on Multi-Agents, (2006).
  2. Sachiyo Arai, Yohei Murakami, Yuki Sugimoto, Toru Ishida, Semantic Web Service Architecture using Multi-agent Scenario Description, 6th Pacific Rim International Workshop on Multi-Agents, pp.98-109, (2003).
  3. Zhiqiang Gao, Sachiyo Arai and Toru Ishida, Social Agents in Digital Cities. Agent cities: Challenges in Open Agent Environments, (2003) .
  4. Sachiyo Arai and Kazuteru Miyazaki, Learning Robust Policies for Uncertain and Stochastic Multi-agent Domains, International Symposium on Artificial Life and Robotics, (2002).
  5. Sachiyo Arai and Katia Sycara, Multi-Agent Reinforcement Learning for Planning and Conflict Resolution in a Dynamic Domain, Proceedings of the 4th International Conference on Autonomous Agents , pp. 104-105, (2000).
  6. Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Cranes Control Using Multi-agent Reinforcement Learning, International Conference on Intelligent Autonomous Systems, Vol.5, pp. 335-342, (1998).
  7. Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Learning Cooperative Behavior by Profit Sharing Agents, Proceedings of the 15th International Joint Conference on Artificial Intelligence, p.7, (1997)
  8. Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Generating Cooperative Behavior by Multi-Agent Reinforcement Learning, Proceedings of the 6th European Workshop on Learning Robots, pp. 111-120, (1997) .
  9. Sachiyo Arai, Masayuki Yamamura, and Shigenobu Kobayashi, Horizontal and Vertical Cooperation by Multi-agents for Dynamic Planning, Proceedings of the 1st Pacific Rim International Conference on Artificial Intelligence, pp.77-82, (1990).
  10. Sachiyo Arai, Masayuki Yamamura, and Shigenobu Kobayashi, Model of Problem Decomposition in Cooperative Planning, Proceedings of the 28th SICE Annual Conference, Vol.2, pp.1255-1258, (1989).

Review and Commentary Articles

  1. Sachiyo Arai (2013) Applying Inverse Reinforcement Learning to Reward Design in Multiagent Domains. : Journal of the Society of Instrument and Control Engineers, Vol.52 No.6, 2013-6, p.534-539, The Society of Instrument and Control Engineers, CORONA PUBLISHING CO.,LTD.
  2. Akira Namatame, Sachiyo Arai (2005) Interaction among Multiple Agents. Journal of the Society of Instrument and Control Engineers, Vol.44, No.12, pp. 865-874, The Society of Instrument and Control Engineers, CORONA PUBLISHING CO.,LTD.
  3. Sachiyo Arai (2001) Multiagent Reinforcement Learning Frameworks : Steps toward Practical Use. The Japanese Society for Artificial Intelligence, Vol.16, No.4, 476-481, Ohmsha, Ltd.

Books

  1. Reinforcement Learning in the Future, Morikita Publishing Co., Ltd., Coauthor, Chap.2 and Chap.3, 2016.10.27.
  2. Electrical Engineering Handbook, 7th Edition. Vol.07 Controls and Systems, Chap.7.Sec.4. Reinforcement Learning and Multiagent, 2013.9.
  3. Electrical Engineering Handbook, 7th Edition. Vol.34 Information Processing Systems, Chap.6. Artificial Intelligence, 2013.9.
  4. IEEJ Technical Reports, Real world and agent simulation, Chap.4 Emergence method of social norm in micro simulation, 2012.7.
  5. IEEJ Technical Reports, Vol.1273, Research Committee on Machine Learning Technology Research for Practical Application.
  6. Multiagent Applications with Evolutionary Computation and Biologically Inspired Technologies: Intelligent Techniques for Ubiquity and Optimization. IGI GLOBAL, Coauthor, 2010.8.

Awards

Research

  • 2017.09.
    Excellent Paper Award @ Joint Agent Workshops & Symposium 2017

    Ryosuke Saitake, Shota Takeki, Sachiyo Arai. Multiobjective reinforcement learning algorithm by nonlinear scalarization of expected reward vector. (Japanese)
  • 2017.09.
    Excellent Poster Award @ Joint Agent Workshops & Symposium 2017

    Keiichi Namikoshi, Sachiyo Arai. Strategy extraction from human flow data considering tracking agents.(Japanese)
  • 2017.09.
    Excellent Poster Award @ Joint Agent Workshops & Symposium 2017

    Shota Ishikawa, Sachiyo Arai. Simultaneous estimation of reward and feature vector for learning driving of an expert driver. (Japanese)
  • 2017.09.
    Excellent Presentation Award @ Joint Agent Workshops & Symposium 2016

    Yusuke Nakata, Sachiyo Arai. Feature Extraction for Design Affordance Based on Analysis of Hidden Layer of Deep Neural Network. (Japanese)
  • 2016.03.
    Award of Excellence @ 16th Multi Agent System Competition

    Yoko Hino. Avoiding man-made disasters in the railway restoration process during disasters on major railway networks in the metropolitan area. (Japanese)
  • 2015.10.
    Excellent Poster Award @ Joint Agent Workshops & Symposium 2015

    Keiichi Namikoshi, Sachiyo Arai. Identification of norms of pedestrian behavior based on walking trajectories.(Japanese)
  • 2012.10
    Sponsor Award @ Joint Agent Workshops & Symposium 2012

    Shun Kagaya, Sachiyo Arai. Inter-regional power interchange by reinforcement learning agent. (Japanese)
  • 2012.06.
    Award of Excellence @ The 26th Annual Conference of the Japanese Society for Artificial Intelligence, 2012

    Kanako Suzuki, Amane Okita, Sachiyo Arai. Inverse Reinforcement learning to Play an Optimal Nash Equilibrium in Multiagent System. (Japanese)
  • 2010.06.18
    Invited Lecture @ The 24th Annual Conference of the Japanese Society for Artificial Intelligence, 2010

    Theme setting as "when in Rome, do as the Romans do" (Japanese)
  • 2010.
    Best Presentation Award @ Multiagent Workshop 2010

    Kanako Suzuki
  • 2010.03.10
    Student Encouragement Award @ 72nd National Convention of IPSJ 2010, 50th Anniversary.

    Hideaki Uchida, Sachiyo Arai. Learning Strategy of Effective Information Services for Indirect Traffic Control.(Japanese)

Education

  • 2009.09. : Best Professor Award (Dept. Urban Environment Systems, Chiba Univ.) Subsequent awards are abolished
  • 2008.11. : Best Professor Award All faculties in Chiba Univ.)
  • 2007.09. : Best Professor Award (Dept. Urban Environment Systems, Chiba Univ.)

External Funds

Fellowship

  • 2014.04 - now: Takenaka Corporation

Joint Research

  • 2017 .08 - now: Honda R&D Co.,Ltd.

Patents

  • Videotex Terminal, Sachiyo Arai(Tan), Masami Kogun, G09G 5/00 510 G 9471-5G (International Patent Classification Ver.6), 1987-04-02
JAPANESE