Presentation 2012-11-08
Adaptive Ability of Concurrent Q Learning, Sarsa and Q Learning to Dynamical Environment
Kazunori MURAKAMI, Tomoko OZEKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we compare the performance of Sarsa, Q learning and concurrent Q learning, one of the adaptive techniques for dynamic environment in the field of reinforcement learning. In reinforcement learning in maze, we validate what kind of behavior each technique shows for the change of a destination or the obstacle.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reinforcement learning / Dynamic environment / Concurrent Q learning
Paper # IBISML2012-67
Date of Issue

Conference Information
Committee IBISML
Conference Date 2012/10/31(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 Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Adaptive Ability of Concurrent Q Learning, Sarsa and Q Learning to Dynamical Environment
Sub Title (in English)
Keyword(1) Reinforcement learning
Keyword(2) Dynamic environment
Keyword(3) Concurrent Q learning
1st Author's Name Kazunori MURAKAMI
1st Author's Affiliation Graduate school of the Engineering, Tokai University()
2nd Author's Name Tomoko OZEKI
2nd Author's Affiliation Department of Human and Information Science, Tokai University
Date 2012-11-08
Paper # IBISML2012-67
Volume (vol) vol.112
Number (no) 279
Page pp.pp.-
#Pages 5
Date of Issue