机构

• 自动化研究所 [11]
• 合肥物质科学研究院 [1]

采集方式

• OAI收割 [12]

内容类型

• 期刊论文 [11]
• 会议论文 [1]

发表日期

• 2024 [1]
• 2023 [3]
• 2022 [1]
• 2021 [1]
• 2020 [1]
• 2019 [1]
• 更多

学科主题

筛选

浏览/检索结果: 共12条，第1-10条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 Contrastive Correlation Preserving Replay for Online Continual Learning 期刊论文  OAI收割 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 卷号: 34, 期号: 1, 页码: 124-139 作者:  Yu, Da;  Zhang, Mingyi;  Li, Mantian;  Zha, Fusheng;  Zhang, Junge   |  收藏  |  浏览/下载：27/0  |  提交时间：2024/03/26 Task analysis  Correlation  Knowledge transfer  Training  Memory management  Data models  Mutual information  Continual learning  catastrophic forgetting  class-incremental learning  experience replay   Relay Hindsight Experience Replay: Self-guided continual reinforcement learning for sequential object manipulation tasks with sparse rewards 期刊论文  OAI收割 NEUROCOMPUTING, 2023, 卷号: 557 作者:  Luo, Yongle;  Wang, Yuxin;  Dong, Kun;  Zhang, Qiang;  Cheng, Erkang   |  收藏  |  浏览/下载：37/0  |  提交时间：2023/11/10 Deep reinforcement learning  Robotic manipulation  Continual learning  Hindsight experience replay  Sparse reward   A Data-Based Feedback Relearning Algorithm for Uncertain Nonlinear Systems 期刊论文  OAI收割 IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 5, 页码: 1288-1303 作者:  Chaoxu Mu;  Yong Zhang;  Guangbin Cai;  Ruijun Liu;  Changyin Sun   |  收藏  |  浏览/下载：10/0  |  提交时间：2023/04/26 Data episodes  experience replay  neural networks  reinforcement learning (RL)  uncertain systems   Squeezing More Past Knowledge for Online Class-Incremental Continual Learning 期刊论文  OAI收割 IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 3, 页码: 722-736 作者:  Da Yu;  Mingyi Zhang;  Mantian Li;  Fusheng Zha;  Junge Zhang   |  收藏  |  浏览/下载：17/0  |  提交时间：2023/03/02 Catastrophic forgetting  class-incremental learning  continual learning (CL)  experience replay   Barrier-Certified Learning-Enabled Safe Control Design for Systems Operating in Uncertain Environments 期刊论文  OAI收割 IEEE/CAA Journal of Automatica Sinica, 2022, 卷号: 9, 期号: 3, 页码: 437-449 作者:  Zahra Marvi;  Bahare Kiumarsi   |  收藏  |  浏览/下载：19/0  |  提交时间：2022/03/09 Control barrier functions (CBFs)  experience replay  learning  safety-critical systems  uncertainty   A Novel Heterogeneous Actor-critic Algorithm with Recent Emphasizing Replay Memory 期刊论文  OAI收割 International Journal of Automation and Computing, 2021, 卷号: 18, 期号: 4, 页码: 619-631 作者:  Bao Xi;  Rui Wang;  Shuo Wang;  Ying-Hao Cai   |  收藏  |  浏览/下载：18/0  |  提交时间：2021/07/20 Reinforcement learning (RL)  actor-critic  experience replay  training efficiency  manipulation skill learning   Path Planning for Intelligent Robots Based on Deep Q-learning With Experience Replay and Heuristic Knowledge 期刊论文  OAI收割 IEEE/CAA Journal of Automatica Sinica, 2020, 卷号: 7, 期号: 4, 页码: 1179-1189 作者:  Lan Jiang;  Hongyun Huang;  Zuohua Ding   |  收藏  |  浏览/下载：21/0  |  提交时间：2021/03/11 Deep Q-learning (DQL)  experience replay (ER)  heuristic knowledge (HK)  path planning   Adaptive cruise control via adaptive dynamic programming with experience replay 期刊论文  OAI收割 SOFT COMPUTING, 2019, 卷号: 23, 期号: 12, 页码: 4131-4144 作者:  Wang, Bin;  Zhao, Dongbin;  Cheng, Jin   |  收藏  |  浏览/下载：52/0  |  提交时间：2019/07/11 Adaptive cruise control  Adaptive dynamic programming  Experience replay  Reinforcement learning  Neural networks   Adaptive Q-Learning for Data-Based Optimal Output Regulation With Experience Replay 期刊论文  OAI收割 IEEE TRANSACTIONS ON CYBERNETICS, 2018, 卷号: 48, 期号: 12, 页码: 3337-3348 作者:  Luo, Biao;  Yang, Yin;  Liu, Derong   |  收藏  |  浏览/下载：55/0  |  提交时间：2019/01/08 Data-based  experience replay  neural networks (NNs)  off-policy  optimal control  Q-learning (QL)   Comprehensive comparison of online ADP algorithms for continuous-time optimal control 期刊论文  OAI收割 ARTIFICIAL INTELLIGENCE REVIEW, 2018, 卷号: 49, 期号: 4, 页码: 531-547 作者:  Zhu, Yuanheng;  Zhao, Dongbin   |  收藏  |  浏览/下载：21/0  |  提交时间：2017/09/13 Adaptive Dynamic Programming  Policy Iteration  Integral Reinforcement Learning  Experience Replay  Off-policy