Presentation 2009-07-13
Composition of Feature Space and State Space Dynamics Models for Model-based Reinforcement Learning
Akihiko YAMAGUCHI, Jun TAKAMATSU, Tsukasa OGASAWARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Learning a dynamics model and a reward model during reinforcement learning is a useful way, since the agent can also update its value function by using the models. In this paper, we propose a general dynamics model that is a composition of the feature space dynamics model and the state space dynamics model. This way enables to obtain a good generalization from a small number of samples because of the linearity of the state space dynamics, while it does not lose the accuracy. We demonstrate the simulation comparison of some dynamics models used together with a Dyna algorithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Model-based reinforcement learning / Dyna-style planning / prioritized sweeping / dynamics model
Paper # NLP2009-15,NC2009-8
Date of Issue

Conference Information
Committee NLP
Conference Date 2009/7/6(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 Nonlinear Problems (NLP)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Composition of Feature Space and State Space Dynamics Models for Model-based Reinforcement Learning
Sub Title (in English)
Keyword(1) Model-based reinforcement learning
Keyword(2) Dyna-style planning
Keyword(3) prioritized sweeping
Keyword(4) dynamics model
1st Author's Name Akihiko YAMAGUCHI
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Jun TAKAMATSU
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name Tsukasa OGASAWARA
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 2009-07-13
Paper # NLP2009-15,NC2009-8
Volume (vol) vol.109
Number (no) 124
Page pp.pp.-
#Pages 6
Date of Issue