Presentation 2002/12/6
A Parameter Control Method Inspired from Neuromodulators in Reinforcement Learning
Junya MIZUNO, Kazushi MURAKOSHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The brain gains appropriate behaviors which gets rewards and escapes punishments by trial and error. Reinforcement learning models such a nature's system by an engineering approach. Neuromodulators, which projects widely in brain and adjusts functions in each brain part, are matched with internal parameters of reinforcement learning. We propose a reinforcement learning algorithm which can follow sudden changes in environment by considering how neuromodulators affect behaviors. This method improves actions by controlling the internal parameters of reinforcement learning after the obtained reward decreased as compared with the past. We actually applied this algorithm to learning problems, with the result that it followed sudden changes in environment.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reinforcement Learning / sudden changes in environment / noradrenaline / acetylcholine / serotonin
Paper # NC2002-102
Date of Issue

Conference Information
Committee NC
Conference Date 2002/12/6(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) A Parameter Control Method Inspired from Neuromodulators in Reinforcement Learning
Sub Title (in English)
Keyword(1) Reinforcement Learning
Keyword(2) sudden changes in environment
Keyword(3) noradrenaline
Keyword(4) acetylcholine
Keyword(5) serotonin
1st Author's Name Junya MIZUNO
1st Author's Affiliation Department of Knowledge-based Information Engineering, Toyohashi University of Technology()
2nd Author's Name Kazushi MURAKOSHI
2nd Author's Affiliation Department of Knowledge-based Information Engineering, Toyohashi University of Technology
Date 2002/12/6
Paper # NC2002-102
Volume (vol) vol.102
Number (no) 508
Page pp.pp.-
#Pages 6
Date of Issue