Kei Matsubayashi

Learn More
Reinforcement learning is a technique to learn suitable action policies that maximize utility, via the clue of reinforcement signals: reward or punishment. Q-learning, a widely used reinforcement learning method, has been analyzed in much research on autonomous agents. However, as the size of the problem space increases , agents need more computational(More)
In multi-agent environments where agents independently generate and execute plans to satisfy their goals, the resulting plans may sometimes overlap. In this paper, we propose a collaboration mechanism using social law, through which rational agents can smoothly delegate and receive the execution of the overlapping parts of plans in order to reduce the cost(More)
Acknowledgments This study has been completed with the benet of advice from many people during my Master and Ph.D. courses at Keio University. Here, I express my thanks to them for their ideas and suggestions. It is my great pleasure to thank Prof. Masakazu Nakanishi, my adviser, for his encouragement and for support throughout my undergraduate and graduate(More)
x Abstract In Distributed Problem Solving (DPS), Dynamic Reorganization is said to be eective in order to cope with tradeos between the global accuracy and the e-ciency of the problem solving. In order to realize an architecture for the Dynamic Reorganization, it is important to consider a question \When should agents reorganize ? ". Such architectures,(More)
  • 1