中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 复杂系统认知与决策实验室
  5. 决策指挥与体系智能
OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research

文献类型：期刊论文

作者Li, Kai1,3; Xu, Hang1,3; Zhao, Enmin1,3; Wu, Zhe1,3; Xing, Junliang2
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2023-06-14
页码15
关键词Artificial intelligence (AI) benchmark imperfect-information game Nash equilibrium no-limit Texas hold'em (NLTH)
ISSN号2162-237X
DOI10.1109/TNNLS.2023.3280186
通讯作者Xing, Junliang(jlxing@tsinghua.edu.cn)
英文摘要Owing to the unremitting efforts from a few institutes, researchers have recently made significant progress in designing superhuman artificial intelligence (AI) in no-limit Texas hold'em (NLTH), the primary testbed for large-scale imperfect-information game research. However, it remains challenging for new researchers to study this problem since there are no standard benchmarks for comparing with existing methods, which hinders further developments in this research area. This work presents OpenHoldem, an integrated benchmark for large-scale imperfect-information game research using NLTH. OpenHoldem makes three main contributions to this research direction: 1) a standardized evaluation protocol for thoroughly evaluating different NLTH AIs; 2) four publicly available strong baselines for NLTH AI; and 3) an online testing platform with easy-to-use APIs for public NLTH AI evaluation. We will publicly release OpenHoldem and hope it facilitates further studies on the unsolved theoretical and computational issues in this area and cultivates crucial research problems like opponent modeling and human-computer interactive learning.
WOS关键词LEVEL ; GO ; POKER ; ALGORITHM ; SHOGI ; CHESS
资助项目National Key Research and Development Program of China[2022ZD0116401] ; Natural Science Foundation of China[62076238] ; Natural Science Foundation of China[62222606] ; Natural Science Foundation of China[61902402] ; China Computer Federation (CCF)-Tencent Open Fund ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA27000000]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001012538800001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China ; Natural Science Foundation of China ; China Computer Federation (CCF)-Tencent Open Fund ; Strategic Priority Research Program of the Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/53570]  
专题融合创新中心_决策指挥与体系智能
通讯作者Xing, Junliang
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Li, Kai,Xu, Hang,Zhao, Enmin,et al. OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:15.
APA Li, Kai,Xu, Hang,Zhao, Enmin,Wu, Zhe,&Xing, Junliang.(2023).OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,15.
MLA Li, Kai,et al."OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):15.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。