Swarm Reinforcement Learning Algorithm Based on Particle Swarm Optimization Whose Personal Bests Have Lifespans
作者： Hitoshi Iima , Yasuaki Kuroe
DOI: 10.1007/978-3-642-10684-2_19
关键词: Artificial intelligence 、 Swarm intelligence 、 Mathematical optimization 、 Multi-swarm optimization 、 Particle swarm optimization 、 Reinforcement learning 、 Swarm behaviour 、 Computer science 、 Reinforcement learning algorithm
摘要: We recently proposed a swarm reinforcement learning algorithm based on particle optimization (PSO) in order to find optimal policies rapidly. In this algorithm, multiple agents are prepared, and they learn not only by individual but also an update procedure of PSO. procedure, state-action values updated the personal best global which found so far. paper, we direct our attention problem that overvaluing bests brings inferior performance. overvalued best, propose PSO each agent has lifespan.
springer.com
springerlink.com
acm.org 参考文章(9)
Christopher J. C. H. Watkins, Peter Dayan, Technical Note : \cal Q -Learning Machine Learning. ,vol. 8, pp. 279- 292 ,(1992) , 10.1007/BF00992698
Christopher J.C.H. Watkins, Peter Dayan, Technical Note Q-Learning Machine Learning. ,vol. 8, pp. 279- 292 ,(1992) , 10.1023/A:1022676722315
Lucian Busoniu, Robert Babuska, Bart De Schutter, A Comprehensive Survey of Multiagent Reinforcement Learning systems man and cybernetics. ,vol. 38, pp. 156- 172 ,(2008) , 10.1109/TSMCC.2007.913919
Jim Pugh, Alcherio Martinoli, Multi-robot learning with particle swarm optimization Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems - AAMAS '06. pp. 441- 448 ,(2006) , 10.1145/1160633.1160715
Hitoshi Iima, Yasuaki Kuroe, Swarm reinforcement learning algorithms based on particle swarm optimization systems, man and cybernetics. pp. 1110- 1115 ,(2008) , 10.1109/ICSMC.2008.4811430
J. Pugh, A. Martinoli, Yizhen Zhang, Particle swarm optimization for unsupervised robotic learning ieee swarm intelligence symposium. pp. 92- 99 ,(2005) , 10.1109/SIS.2005.1501607
Hitoshi Iima, Yasuaki Kuroe, Reinforcement Learning through Interaction among Multiple Agents 2006 SICE-ICASE International Joint Conference. pp. 2457- 2462 ,(2006) , 10.1109/SICE.2006.315142
Richard S. Sutton, Reinforcement Learning ,(1992)
Andrew G. Barto, Reinforcement learning The handbook of brain theory and neural networks. pp. 804- 809 ,(1998)