This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
Joel Veness, Kee Siong Ng, Marcus Hutter, William ...
Abstract. The purpose of this paper is (1) to provide a theoretical justification for the use of Monte-Carlo sampling for approximate resolution of NP-hard maximization problems in...
Abstract We present the General Game Playing system Centurio. Centurio is a Java-based player featuring different strategies based on Monte Carlo Tree Search extended by technique...
We describe two Go programs, ¢¡¤£¦¥ and ¢¡¤§¨£ , developed by a Monte-Carlo approach that is simpler than Bruegmann’s (1993) approach. Our method is based on Abra...
Recently, Monte-Carlo Tree Search (MCTS) has advanced the field of computer Go substantially. In the game of Lines of Action (LOA), which has been dominated in the past by αβ, M...