Incentive Learning in Monte Carlo Tree Search
檔案
- 000328732600005.pdf (1.16 MB, Adobe PDF)
日期
2013-12-01
類型
系所
期刊名稱
IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES
卷期與頁次
第 5 卷第 4 期,頁 346–352
ISSN
1943-068X
語言
英文
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.
關鍵詞
Artificial intelligencecombinatorial gamescomputational intelligencecomputer gamesreinforcement learning所屬典藏
期刊論文引用此條目
Kao, K.-Y., Wu, I.-C., Yen, S.-J., & Shan, Y.-C. (2013). Incentive Learning in Monte Carlo Tree Search. IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES, 5(4), 346–352. https://doi.org/10.1109/TCIAIG.2013.2248086
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/23441