Presentation	2007/3/7 A Method to Acquire Effective Evacuation Policy Masayuki OHTA, Tomohisa YAMASHITA, Koichi KURUMATANI,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	We are trying to acquire effective evacuation policies with learning on a multi-agent simulator. In such multi-agent environment, the approach that exchanges information between agents is used to promote learning. However, if the agents have some preferences in their action-selection, the information-exchange may cause some problems. To overcome this problem, we propose a method to decide with which agent to exchange information. The effectiveness of the proposed method is confirmed with simulation of evacuation from underground mall.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)
Paper #	AI2006-34
Date of Issue

Conference Information
Committee	AI
Conference Date	2007/3/7(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	Artificial Intelligence and Knowledge-Based Processing (AI)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	A Method to Acquire Effective Evacuation Policy
Sub Title (in English)
Keyword(1)
1st Author's Name	Masayuki OHTA
1st Author's Affiliation	National Institute of Advanced Industrial Science and Technology (AIST):CREST, Japan Science and Technology Agency (JST)()
2nd Author's Name	Tomohisa YAMASHITA
2nd Author's Affiliation	National Institute of Advanced Industrial Science and Technology (AIST):CREST, Japan Science and Technology Agency (JST)
3rd Author's Name	Koichi KURUMATANI
3rd Author's Affiliation	National Institute of Advanced Industrial Science and Technology (AIST):CREST, Japan Science and Technology Agency (JST)
Date	2007/3/7
Paper #	AI2006-34
Volume (vol)	vol.106
Number (no)	585
Page	pp.pp.-
#Pages	4
Date of Issue