Incentive Learning in Monte Carlo Tree Search
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
352 | en_US |
dc.citation.issue |
4 | en_US |
dc.citation.spage |
346 | en_US |
dc.citation.volume |
5 | en_US |
dc.citation.woscount |
0 | |
dc.contributor.author |
Kao, Kuo-Yuan | en_US |
dc.contributor.author |
Wu, I-Chen | en_US |
dc.contributor.author |
Yen, Shi-Jim | en_US |
dc.contributor.author |
Shan, Yi-Chang | en_US |
dc.contributor.department |
資訊工程學系 | zh_TW |
dc.contributor.department |
Department of Computer Science | en_US |
dc.date.accessioned |
2014-12-08T15:34:07Z | |
dc.date.available |
2014-12-08T15:34:07Z | |
dc.date.issued |
2013-12-01 | en_US |
dc.description.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. | en_US |
dc.identifier.doi |
10.1109/TCIAIG.2013.2248086 | en_US |
dc.identifier.issn |
1943-068X | en_US |
dc.identifier.journal |
IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1109/TCIAIG.2013.2248086 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/23441 | |
dc.identifier.wosnumber |
WOS:000328732600005 | |
dc.language.iso |
en_US | en_US |
dc.subject |
Artificial intelligence | en_US |
dc.subject |
combinatorial games | en_US |
dc.subject |
computational intelligence | en_US |
dc.subject |
computer games | en_US |
dc.subject |
reinforcement learning | en_US |
dc.title |
Incentive Learning in Monte Carlo Tree Search | en_US |
dc.type |
Article | en_US |
檔案
- 000328732600005.pdf (1.16 MB, Adobe PDF)
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