標題: | Incentive Learning in Monte Carlo Tree Search |
作者: | Kao, Kuo-Yuan Wu, I-Chen Yen, Shi-Jim Shan, Yi-Chang 資訊工程學系 Department of Computer Science |
關鍵字: | Artificial intelligence;combinatorial games;computational intelligence;computer games;reinforcement learning |
公開日期: | 1-十二月-2013 |
摘要: | 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 |
期刊: | IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES |
Volume: | 5 |
Issue: | 4 |
起始頁: | 346 |
結束頁: | 352 |
顯示於類別: | 期刊論文 |