CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共3条,第1-3条 帮助

限定条件            
已选(0)清除 条数/页:   排序方式:
Dynamic-horizon model-based value estimation with latent imagination 期刊论文
IEEE Transactions on Neural Networks and Learning Systems, 2022, 页码: 1-14
作者:  Wang JJ(王俊杰);  Zhang QC(张启超);  Zhao DB(赵冬斌)
Adobe PDF(2305Kb)  |  收藏  |  浏览/下载:172/62  |  提交时间:2023/05/30
Latent world model  model-based value expansion (MVE)  reinforcement learning  reinforcement learning  
Empirical Policy Optimization for n-Player Markov Games 期刊论文
IEEE Transactions on Cybernetics, 2022, 页码: doi={10.1109/TCYB.2022.3179775}
作者:  Yuanheng Zhu;  Weifan Li;  Mengchen Zhao;  Jianye Hao;  Dongbin Zhao
Adobe PDF(1739Kb)  |  收藏  |  浏览/下载:99/40  |  提交时间:2023/04/26
Online Minimax Q Network Learning for Two-Player Zero-Sum Markov Games 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 卷号: 33, 期号: 3, 页码: 1228-1241
作者:  Zhu, Yuanheng;  Zhao, Dongbin
Adobe PDF(2838Kb)  |  收藏  |  浏览/下载:221/2  |  提交时间:2022/06/10
Games  Nash equilibrium  Mathematical model  Markov processes  Convergence  Dynamic programming  Training  Deep reinforcement learning (DRL)  generalized policy iteration (GPI)  Markov game (MG)  Nash equilibrium  Q network  zero sum