Presentation 2009-12-21
Synthesis of Desired Space-time Patterns based-on Reinforce Learning
Yoshiaki HACHIYA, Hidehiro NAKANO, Arata MIYAUCHl,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Cellular automata (CA) is used for a image processing and a physical simulation. However, it is very difficlt for designer to synthesize CA according to target systems. Therefore, this research aims to synthesize the desired rule sequence in CA by using a simple Reinforcement Learning. This paper shows typical synthesis results for transition from specific pattern to another specific pattern , transition from random pattern to another random pattern, Self-Repairing and Self-Propagating, and confirms effectiveness of our proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Nonlinear problem / Cellular Automata / Rainforcement Learning / Q-Learning
Paper # NLP2009-134
Date of Issue

Conference Information
Committee NLP
Conference Date 2009/12/14(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 JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Synthesis of Desired Space-time Patterns based-on Reinforce Learning
Sub Title (in English)
Keyword(1) Nonlinear problem
Keyword(2) Cellular Automata
Keyword(3) Rainforcement Learning
Keyword(4) Q-Learning
1st Author's Name Yoshiaki HACHIYA
1st Author's Affiliation Tokyo City University()
2nd Author's Name Hidehiro NAKANO
2nd Author's Affiliation Tokyo City University
3rd Author's Name Arata MIYAUCHl
3rd Author's Affiliation Tokyo City University
Date 2009-12-21
Paper # NLP2009-134
Volume (vol) vol.109
Number (no) 354
Page pp.pp.-
#Pages 5
Date of Issue