Presentation 2014-06-19
Learning of Probability of Dust Accumulation without Communications for Multi-agent Continuous Cleaning
Ayumi SUGIYAMA, Toshiharu SUGAWARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have studied the strategy learning in multi-agent continuous cleaning task in which we assumed that agents knew the probability of dust accumulation in environment, since we paid attention to autonomous strategy learning for coordination. However, in actual environments, agent cannot necessarily get the environmental information in advance. Therefore, we extended the previous method for the environment where agents do not know where are easy to get dirty, which is a part of environment information. The experimented results showed that agents could learn the probability of dust accumulation as well as the appropriate strategies, and in some cases, the performance with the proposed method outperformed the previous method even though some information is missing.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Multi-Agent System / Continuous Cleaning / Multi-Agent Patrolling Problem / Learning / Cooperation
Paper # AI2014-2
Date of Issue

Conference Information
Committee AI
Conference Date 2014/6/12(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) Learning of Probability of Dust Accumulation without Communications for Multi-agent Continuous Cleaning
Sub Title (in English)
Keyword(1) Multi-Agent System
Keyword(2) Continuous Cleaning
Keyword(3) Multi-Agent Patrolling Problem
Keyword(4) Learning
Keyword(5) Cooperation
1st Author's Name Ayumi SUGIYAMA
1st Author's Affiliation Department of Computer Science and Communications Engineering, Waseda University()
2nd Author's Name Toshiharu SUGAWARA
2nd Author's Affiliation Department of Computer Science and Communications Engineering, Waseda University
Date 2014-06-19
Paper # AI2014-2
Volume (vol) vol.114
Number (no) 89
Page pp.pp.-
#Pages 6
Date of Issue