Presentation 2007-06-15
Reinforcement Learning for Cooperative Actions in a Partially Observable Multi-Agent System
Yuki TANIGUCHI, Takeshi MORI, Shin ISHII,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this article, we apply a policy gradient-based reinforcement learning to allowing multiple agents to perform cooperative actions in a partially, observable environment. We introduce an auxiliary state variable, an internal state, whose stochastic process is Markov, for extracting important features of multi-agent's dynamics. Computer simulations show that every agent can identify an appropriate internal state model and acquire a good policy; this approach is shown to be more effective than a traditional memory-based method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Partially observable environments / Internal state / Policy gradient method / Multi-agent system / Cooperative action
Paper # NC2007-15
Date of Issue

Conference Information
Committee NC
Conference Date 2007/6/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Reinforcement Learning for Cooperative Actions in a Partially Observable Multi-Agent System
Sub Title (in English)
Keyword(1) Partially observable environments
Keyword(2) Internal state
Keyword(3) Policy gradient method
Keyword(4) Multi-agent system
Keyword(5) Cooperative action
1st Author's Name Yuki TANIGUCHI
1st Author's Affiliation Nara Institute of Science and Technology()
2nd Author's Name Takeshi MORI
2nd Author's Affiliation Nara Institute of Science and Technology
3rd Author's Name Shin ISHII
3rd Author's Affiliation Nara Institute of Science and Technology
Date 2007-06-15
Paper # NC2007-15
Volume (vol) vol.107
Number (no) 92
Page pp.pp.-
#Pages 5
Date of Issue