eprintid: 20977
rev_number: 11
eprint_status: archive
userid: 1903
dir: disk0/00/02/09/77
datestamp: 2013-11-07 17:58:23
lastmod: 2016-04-21 11:04:38
status_changed: 2013-11-07 17:58:23
type: conference_item
metadata_visibility: show
item_issues_count: 0
creators_name: Zela Moraya, Wester Edison
creators_name: Zato Recellado, Jose Gabriel
title: Evolving and coevolving computer go players using neuroevolution.
ispublished: unpub
subjects: informatica
keywords: Go, evolution, Coevolution, Neuroevolution, SANE, SANEi, Evolución, Coevolución, Neuroevolución.
abstract: The Go game is ancient very complex game with simple rules which still is a challenge for the AI.This work cover some neuroevolution techniques used in reinforcement learning applied to the GO game as SANE (Symbiotic Adaptive Neuro-Evolution) and presents a variation to this method with the intention of evolving better strategies in the game. The computer Go player based in SANE is evolved againts a knowed player which creates some problem as determinism for which is proposed the co-evolution. Finally, it is introduced an algorithm to co-evolve two populations of neurons to evolve better computer Go players.
date: 2011
date_type: published
official_url: http://www.complexity2011.org
full_text_status: public
pres_type: paper
pages: 10
event_title: COPCOM 2011 1st International Workshop on Coping with Complexity
event_location: Oct 19, 2011 - Oct 20, 2011
event_dates: Cluj-Napoca, Romania
event_type: conference
institution: Informatica
department: otro
refereed: TRUE
rights: by-nc-nd
citation:   Zela Moraya, Wester Edison and Zato Recellado, Jose Gabriel  (2011).  Evolving and coevolving computer go players using neuroevolution..  In: "COPCOM 2011 1st International Workshop on Coping with Complexity", Cluj-Napoca, Romania, Oct 19, 2011 - Oct 20, 2011.    
document_url: https://oa.upm.es/20977/1/INVE_MEM_2011_131048.pdf