Knowledge Commons of Institute of Automation,CAS
Enhanced Rolling Horizon Evolution Algorithm With Opponent Model Learning: Results for the Fighting Game AI Competition | |
Zhentao Tang1,2; Yuanheng Zhu1,2; Dongbin Zhao1,2; Simon M. Lucas3 | |
发表期刊 | IEEE TRANSACTIONS ON GAMES |
ISSN | 2475-1502 |
2023 | |
卷号 | 5期号:1页码:5 - 15 |
通讯作者 | Zhao, Dongbin(dongbin.zhao@ia.ac.cn) |
摘要 | The Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for 2-player video game AI: large action space, diverse styles of characters and abilities, and the real-time nature. We propose a novel algorithm that combines Rolling Horizon Evolution Algorithm (RHEA) with opponent model learning. The approach is readily applicable to any 2-player video game. In contrast to conventional RHEA, an opponent model is proposed and is optimized by supervised learning with cross-entropy and reinforcement learning with policy gradient and Q-learning respectively, based on history observations from opponent. The model is learned during the live gameplay. With the learned opponent model, the extended RHEA is able to make more realistic plans based on what the opponent is likely to do. This tends to lead to better results. We compared our approach directly with the bots from the FTGAIC 2018 competition, and found our method to significantly outperform all of them, for all three character. Furthermore, our proposed bot with the policy- gradient-based opponent model is the only one without using Monte-Carlo Tree Search (MCTS) among top five bots in the 2019 competition in which it achieved second place, while using much less domain knowledge than the winner. |
关键词 | Rolling horizon evolution opponent model reinforcement learning supervised learning fighting game |
DOI | 10.1109/TG.2020.3022698 |
关键词[WOS] | GO |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China |
项目资助者 | National Key Research and Development Program of China |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Software Engineering |
WOS记录号 | WOS:001121975100008 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 强化与进化学习 |
国重实验室规划方向分类 | 开放博弈基础理论 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/45042 |
专题 | 多模态人工智能系统全国重点实验室_深度强化学习 |
通讯作者 | Dongbin Zhao |
作者单位 | 1.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China 3.Department of Electronic Engineering and Computer Engineering (EECS), Queen Mary University of London, London E1 4NS, U.K |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhentao Tang,Yuanheng Zhu,Dongbin Zhao,et al. Enhanced Rolling Horizon Evolution Algorithm With Opponent Model Learning: Results for the Fighting Game AI Competition[J]. IEEE TRANSACTIONS ON GAMES,2023,5(1):5 - 15. |
APA | Zhentao Tang,Yuanheng Zhu,Dongbin Zhao,&Simon M. Lucas.(2023).Enhanced Rolling Horizon Evolution Algorithm With Opponent Model Learning: Results for the Fighting Game AI Competition.IEEE TRANSACTIONS ON GAMES,5(1),5 - 15. |
MLA | Zhentao Tang,et al."Enhanced Rolling Horizon Evolution Algorithm With Opponent Model Learning: Results for the Fighting Game AI Competition".IEEE TRANSACTIONS ON GAMES 5.1(2023):5 - 15. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Enhanced Rolling Hor(7686KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论