Presentation 2011-07-26
Modeling and estimating passive dynamics distributions in linearly solvable Markov decision processes
Mauricio BURDELIS, Kazushi IKEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Todorov has recently introduced a class of linearly-solvable Markov decision processes (LSMDPs) which greatly simplifies reinforcement learning. Under some specific conditions, the problem of choosing optimal actions becomes linear, and the optimal transition probabilities can be obtained analytically. In order to apply the LSMDPs framework to realistic problems, it is necessary to know the passive dynamics distribution, which is crucial in the theory. The purpose of the present work is to propose a method to estimate the passive dynamics distribution in reinforcement learning problems.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Linear Bellman Equation / Reinforcement Learning
Paper # NC2011-43
Date of Issue

Conference Information
Committee NC
Conference Date 2011/7/18(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Modeling and estimating passive dynamics distributions in linearly solvable Markov decision processes
Sub Title (in English)
Keyword(1) Linear Bellman Equation
Keyword(2) Reinforcement Learning
1st Author's Name Mauricio BURDELIS
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Kazushi IKEDA
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 2011-07-26
Paper # NC2011-43
Volume (vol) vol.111
Number (no) 157
Page pp.pp.-
#Pages 6
Date of Issue