Title :
A Dynamical Systems Approach for Static Evaluation in Go
Author_Institution :
Brock Univ., St. Catharines, ON, Canada
fDate :
6/1/2011 12:00:00 AM
Abstract :
In the paper, arguments are given as to why the concept of static evaluation has the potential to be a useful extension to Monte Carlo tree search. A new concept of modeling static evaluation through a dynamical system is introduced and strengths and weaknesses are discussed. The general suitability of this approach is demonstrated.
Keywords :
Monte Carlo methods; computer games; knowledge engineering; Monte Carlo tree search; dynamical systems; static evaluation modeling; Computational modeling; Computers; Games; Humans; Monte Carlo methods; Pattern matching; Shape; Artificial intelligence; computational and artificial intelligence; computer Go; discrete dynamical systems; mathematics; nonlinear dynamical systems; nonlinear systems; numerical analysis; relaxation mathods; static evaluation;
Journal_Title :
Computational Intelligence and AI in Games, IEEE Transactions on
DOI :
10.1109/TCIAIG.2011.2141669
