MEBRL: Memory-Evolution-Based Reinforcement Learning Algorithm of MAS
A memory-evolution-based MAS reinforcement learning algorithm (MEBRL) inspired by a psychology memory model is presented. 3 types of different memory stores are used in the design of the algorithm and Learning Automata is used in the processes of agent memory evolution. Through the memory evolution procedure, the agent in the MAS could make a proper decision and share its information indirectly. A multi-agent multi-resource stochastic system model is used to illustrate the performance of the algorithm, and the comparison of the memory-evolution-based MAS reinforcement learning algorithm and other MAS learning algorithm is given.
Unable to display preview. Download preview PDF.
- 1.P. Stone, M. Veloso, Multiagent Systems: A Survey from a Machine Learning Perspective, Autonomous Robotics, 8 (3), 2000.Google Scholar
- 3.N. Ono, K. Fukumoto, Multi-agent Reinforcement Learning: A Modular Approach, Proceedings of the Second International Conference on Multi-Agent Systems, 252–258, 1996.Google Scholar
- 4.K. Najim, A. S. Poznyak, Learning Automata: Theory and Applications, Pergamon Press, Oxford, 1994.Google Scholar
- 5.M.W. Eysenck, M. T. Keane, Cognitive Psychology: A Students Handbook ( 3rd edition ), East Sussex, Psychology Press, 1997.Google Scholar