Presentation 2003/1/28
Adjustment of Discount Rate Using Index for Progress of Learning
Naoko OGAWA, Akio NAMIKI, Masatoshi ISHIKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We show that it can be effective to adjust the discount rate using an index for progress of learning. In the strategy that we propose, the discount rate is small when the learning does not progress enough, and is increased as the learning advances. We also propose three methods for its adjustment ; exponential, by TD error, and by reliability, which are verificated by numerical experiments for a windy gridworld task.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reinforcement Learning / Discount Rate / Progress of Learning / Reliability / Windy Gridworld Task
Paper # NC2002-129
Date of Issue

Conference Information
Committee NC
Conference Date 2003/1/28(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) Adjustment of Discount Rate Using Index for Progress of Learning
Sub Title (in English)
Keyword(1) Reinforcement Learning
Keyword(2) Discount Rate
Keyword(3) Progress of Learning
Keyword(4) Reliability
Keyword(5) Windy Gridworld Task
1st Author's Name Naoko OGAWA
1st Author's Affiliation Graduate School of Information Science and Technology, Univ. of Tokyo()
2nd Author's Name Akio NAMIKI
2nd Author's Affiliation CREST, JST:Graduate School of Information Science and Technology, Univ. of Tokyo
3rd Author's Name Masatoshi ISHIKAWA
3rd Author's Affiliation Graduate School of Information Science and Technology, Univ. of Tokyo
Date 2003/1/28
Paper # NC2002-129
Volume (vol) vol.102
Number (no) 628
Page pp.pp.-
#Pages 6
Date of Issue