Presentation	2006-03-17 Multi-Agent Reinforcement Learning for Pursuit Games Tetsuaki Nakagawa, Masumi Ishikawa,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Recently, there have been many studies on multi-agent systems. Various methods in reinforcement learning have been used for the learning of multi-agent systems. but the learning is difficult due to the explosion of state space, the concurrent learning problem, and the credit assignment problem. To ameliorate the difficulty of the explosion of state space, we propose to drastically decrease the number of states by decomposing a state space into multiple subspaces, combining them. and carrying out reinforcement learning in the combined state space.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	multi-agent / reinforcement learning
Paper #	NC2005-155
Date of Issue

Conference Information
Committee	NC
Conference Date	2006/3/10(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)	Multi-Agent Reinforcement Learning for Pursuit Games
Sub Title (in English)
Keyword(1)	multi-agent
Keyword(2)	reinforcement learning
1st Author's Name	Tetsuaki Nakagawa
1st Author's Affiliation	Graduate School of Life Science and System Engineering, Kyushu Institute of Technology()
2nd Author's Name	Masumi Ishikawa
2nd Author's Affiliation	Graduate School of Life Science and System Engineering, Kyushu Institute of Technology
Date	2006-03-17
Paper #	NC2005-155
Volume (vol)	vol.105
Number (no)	659
Page	pp.pp.-
#Pages	6
Date of Issue