摘要: In this paper we propose a Multi-Agent version of UCT Monte Carlo Go. We use the emergent behavior great number simple agents to increase quality simulations, increasing strength artificial player as whole. Instead one agent playing against itself, different play in simulation phase algorithm, leading better exploration search space. could significantly overcome Fuego, top Computer Go software. Emergent seems be next step development.
acm.org
sci-hub.st 参考文章(35)
Jr. Kenneth Joseph Friedenbach, Abstraction hierarchies: a model of perception and cognition in the game of go University of California, Santa Cruz. ,(1980)
Martin Müller, Computer go as a sum of local games: an application of combinatorial game theory ETH Zürich. ,(1995) , 10.3929/ETHZ-A-001440588
L.V. Allis, Searching for solutions in games and artificial intelligence Ph. D. Thesis, University of Limburg. ,(1994)
Markus Enzenberger, Martin Müller, A lock-free multithreaded monte-carlo tree search algorithm advances in computer games. ,vol. 6048, pp. 14- 20 ,(2009) , 10.1007/978-3-642-12993-3_2
Erik C. D. van der Werf, H. Jaap van den Herik, Jos W. H. M. Uiterwijk, Solving Go on small boards ICGA Journal. ,vol. 26, pp. 92- 107 ,(2003) , 10.3233/ICG-2003-26205
Guillaume M. J. -B. Chaslot, Mark H. M. Winands, H. Jaap van den Herik, Parallel Monte-Carlo Tree Search Computers and Games. pp. 60- 71 ,(2008) , 10.1007/978-3-540-87608-3_6
Daniel Edwards, Timothy Hart, The Alpha-Beta Heuristic Massachusetts Institute of Technology. ,(1963)
Tristan Cazenave, Système d'apprentissage par auto-observation : Application au jeu de go Paris 6. ,(1996)
Bruno Bouzy, Modelisation cognitive du joueur de go Paris 6. ,(1995)
Rémi Coulom, Efficient selectivity and backup operators in Monte-Carlo tree search annual conference on computers. pp. 72- 83 ,(2006) , 10.1007/978-3-540-75538-8_7