|
已选(0)清除
条数/页： 排序方式： |
| An Improved Minimax-Q Algorithm Based on Generalized Policy Iteration to Solve a Chaser-Invader Game 会议论文
, 线上, 2020-5
作者: Liu MS(刘民颂) ; Zhu YH(朱圆恒); Zhao DB(赵冬斌)
 Adobe PDF(727Kb) |  收藏 | 浏览/下载：25/11 | 提交时间：2024/07/04 |
| Boosting On-Policy Actor–Critic With Shallow Updates in Critic 期刊论文
IEEE Transactions on Neural Networks and Learning Systems, 2024, 页码: 1-10
作者: Luntong Li; Yuanheng Zhu
Adobe PDF(9953Kb) | 收藏 | 浏览/下载：49/16 | 提交时间：2024/06/05 |
| MAT: Morphological Adaptive Transformer for Universal Morphology Policy Learning 期刊论文
IEEE Transactions on Cognitive and Developmental Systems, 2024, 页码: 1-12
作者: Boyu Li; Haran Li; Yuanheng Zhu; Dongbin Zhao
Adobe PDF(9953Kb) | 收藏 | 浏览/下载：34/10 | 提交时间：2024/06/05 |
| FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game 期刊论文
IEEE Transactions on Emerging Topics in Computational Intelligence, 2024, 页码: 1-13
作者: Guangzheng Hu; Yuanheng Zhu; Haoran Li; Dongbin Zhao
Adobe PDF(2144Kb) | 收藏 | 浏览/下载：47/9 | 提交时间：2024/06/05
Games Q-learning Task analysis Optimization Convergence Training Nash equilibrium Multi-agent reinforcement learning minimax-Q learning two-team zero-sum Markov games |
| Advantage Constrained Proximal Policy Optimization in Multi-Agent Reinforcement Learning 会议论文
, 昆士兰, 2023-6
作者: Li WF(李伟凡); Zhu YH(朱圆恒); Zhao DB(赵冬斌)
Adobe PDF(4104Kb) | 收藏 | 浏览/下载：261/81 | 提交时间：2023/06/29
multi-agent reinforcement learning policy gradient |
| 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：114/45 | 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：257/14 | 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 |
| Event-Triggered Communication Network With Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 13
作者: Hu, Guangzheng; Zhu, Yuanheng; Zhao, Dongbin; Zhao, Mengchen; Hao, Jianye
Adobe PDF(4187Kb) | 收藏 | 浏览/下载：268/12 | 提交时间：2022/01/27
Bandwidth Protocols Reinforcement learning Task analysis Optimization Communication networks Multi-agent systems Event trigger limited bandwidth multi-agent communication multi-agent reinforcement learning (MARL) |
| Optimal Feedback Control of Pedestrian Flow in Heterogeneous Corridors 期刊论文
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2021, 卷号: 18, 期号: 3, 页码: 1097-1108
作者: Zhu, Yuanheng; Zhao, Dongbin; He, Haibo
Adobe PDF(2666Kb) | 收藏 | 浏览/下载：240/18 | 提交时间：2021/08/15
Microscopy Feedback control Mathematical model Data models Dynamic programming Psychology Computational modeling Adaptive dynamic programming (ADP) heterogeneous corridors macroscopic pedestrian dynamics optimal feedback control pedestrian flow |
| Enhanced Rolling Horizon Evolution Algorithm With Opponent Model Learning: Results for the Fighting Game AI Competition 期刊论文
IEEE TRANSACTIONS ON GAMES, 2023, 卷号: 5, 期号: 1, 页码: 5 - 15
作者: Zhentao Tang; Yuanheng Zhu; Dongbin Zhao; Simon M. Lucas
Adobe PDF(7686Kb) | 收藏 | 浏览/下载：364/76 | 提交时间：2021/07/05
Rolling horizon evolution opponent model reinforcement learning supervised learning fighting game |
