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


文件中的檔案:

  1. 000328732600005.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。