CASIA OpenIR

浏览/检索结果: 共20条,第1-10条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control 会议论文
Advances in Neural Information Processing Systems, New Orleans, USA, 2023-12-10
作者:  Chao Li;  Chen Gong;  Qiang He;  Xinwen Hou
Adobe PDF(1457Kb)  |  收藏  |  浏览/下载:19/5  |  提交时间:2024/05/30
Constrained-cost adaptive dynamic programming for optimal control of discrete-time nonlinear systems 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 卷号: 35, 期号: 3, 页码: 3251 - 3264
作者:  Wei, Qinglai;  Li, Tao
Adobe PDF(8471Kb)  |  收藏  |  浏览/下载:22/9  |  提交时间:2024/05/28
Adaptive dynamic programming  approximate dynamic programming  constrained cost  optimal control  reinforcement learning  
多智能体博弈、学习与控制 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 3, 页码: 580-613
作者:  王龙;  黄锋
Adobe PDF(2088Kb)  |  收藏  |  浏览/下载:16/4  |  提交时间:2024/05/09
博弈论  多智能体学习  控制论  强化学习  人工智能  
基于滚动时域强化学习的智能车辆侧向控制算法 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 12, 页码: 2481-2492
作者:  张兴龙;  陆阳;  李文璋;  徐昕
Adobe PDF(7533Kb)  |  收藏  |  浏览/下载:31/7  |  提交时间:2024/04/17
滚动时域  强化学习  智能汽车  侧向控制  
Multistep Look-Ahead Policy Iteration for Optimal Control of Discrete-Time Nonlinear Systems With Isoperimetric Constraints 期刊论文
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2023, 卷号: 54, 期号: 3, 页码: 1414-1426
作者:  Li, Tao;  Wei, Qinglai;  Wang, Fei-Yue
Adobe PDF(784Kb)  |  收藏  |  浏览/下载:81/8  |  提交时间:2024/02/22
Performance analysis  Optimal control  Dynamic programming  Iterative algorithms  Upper bound  Measurement  Convergence  Adaptive dynamic programming (ADP)  isoperimetric constraints  nonlinear systems  optimal control  policy iteration  
Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 12, 页码: 2233-2247
作者:  Hongyu Ding;  Yuanze Tang;  Qing Wu;  Bo Wang;  Chunlin Chen;  Zhi Wang
Adobe PDF(5205Kb)  |  收藏  |  浏览/下载:108/36  |  提交时间:2023/10/31
Dynamic environments  goal-conditioned reinforcement learning  magnetic field  reward shaping  
Coupled Dynamics and Integrated Control for Position and Attitude Motions of Spacecraft: A Survey 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 12, 页码: 2187-2208
作者:  Feng Zhang;  Guangren Duan
Adobe PDF(1737Kb)  |  收藏  |  浏览/下载:144/45  |  提交时间:2023/10/31
Coupled position and attitude dynamic modeling  integrated position and attitude control  position and attitude coupling analysis  spacecraft  space missions  
An Optimal Control-Based Distributed Reinforcement Learning Framework for A Class of Non-Convex Objective Functionals of the Multi-Agent Network 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 11, 页码: 2081-2093
作者:  Zhe Chen;  Ning Li
Adobe PDF(3366Kb)  |  收藏  |  浏览/下载:69/25  |  提交时间:2023/09/22
Distributed optimization  multi-agent  optimal control  reinforcement learning (RL)  
Privacy Preserving Demand Side Management Method via Multi-Agent Reinforcement Learning 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 10, 页码: 1984-1999
作者:  Feiye Zhang;  Qingyu Yang;  Dou An
Adobe PDF(3841Kb)  |  收藏  |  浏览/下载:85/43  |  提交时间:2023/09/07
Centralized training and decentralized execution  demand side management  multi-agent reinforcement learning  privacy preserving  
执行者-评论家算法框架下的强化学习稳定性研究 学位论文
, 2023
作者:  龚晨
Adobe PDF(8324Kb)  |  收藏  |  浏览/下载:107/6  |  提交时间:2023/06/26
深度强化学习,稳定性,共轭,对抗性攻击,后门攻击