Title: Incentive Learning in Monte Carlo Tree Search
Authors: Kao, Kuo-Yuan
Wu, I-Chen
Yen, Shi-Jim
Shan, Yi-Chang
資訊工程學系
Department of Computer Science
Keywords: Artificial intelligence;combinatorial games;computational intelligence;computer games;reinforcement learning
Issue Date: 1-Dec-2013
Abstract: Monte Carlo tree search (MCTS) is a search paradigm that has been remarkably successful in computer games like Go. It uses Monte Carlo simulation to evaluate the values of nodes in a search tree. The node values are then used to select the actions during subsequent simulations. The performance of MCTS heavily depends on the quality of its default policy, which guides the simulations beyond the search tree. In this paper, we propose an MCTS improvement, called incentive learning, which learns the default policy online. This new default policy learning scheme is based on ideas from combinatorial game theory, and hence is particularly useful when the underlying game is a sum of games. To illustrate the efficiency of incentive learning, we describe a game named Heap-Go and present experimental results on the game.
URI: http://dx.doi.org/10.1109/TCIAIG.2013.2248086
http://hdl.handle.net/11536/23441
ISSN: 1943-068X
DOI: 10.1109/TCIAIG.2013.2248086
Journal: IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES
Volume: 5
Issue: 4
Begin Page: 346
End Page: 352
Appears in Collections:Articles


Files in This Item:

  1. 000328732600005.pdf