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. 多模态人工智能系统全国重点实验室
  5. 深度强化学习
Prototypical Context-Aware Dynamics for Generalization in Visual Control With Model-Based Reinforcement Learning

文献类型：期刊论文

作者Wang, Junjie1,2; Zhang, Qichao1,2; Mu, Yao3; Li, Dong4; Zhao, Dongbin1,2; Zhuang, Yuzheng4; Luo, Ping3; Wang, Bin4; Hao, Jianye4,5
刊名IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
出版日期2024-05-15
页码11
关键词Context-aware dynamics generalization model-based reinforcement learning visual control
ISSN号1551-3203
DOI10.1109/TII.2024.3396525
通讯作者Zhang, Qichao(zhangqichao2014@ia.ac.cn)
英文摘要The latent world model, which efficiently represents high-dimensional observations within a latent space, has shown promise in reinforcement learning-based policies for visual control tasks. Due to a lack of clear environmental context comprehension, its applicability in a variety of contexts with unknown dynamics is constrained. We propose a prototypical context- aware dynamics (ProtoCAD) model to address this issue. This model captures local dynamics using temporally consistent latent contexts and aids generalization in visual control tasks. By grouping prototypes over historical experiences, ProtoCAD collects useful contextual information that improves model-based reinforcement learning dynamics generalization in two ways. First, to guarantee the consistency of prototype assignments for various temporal segments of the same latent trajectory, a temporally consistent prototypes regularizer is used. Then, a context representation is devised to combine the aggregated prototype with the projection embedding of latent states. According to extensive trials, ProtoCAD outperforms competing approaches in terms of dynamics generalization for visual robotic control and autonomous driving applications.
资助项目National Key Research and Development Program of China
WOS研究方向Automation & Control Systems ; Computer Science ; Engineering
语种英语
WOS记录号WOS:001226155200001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China
源URL[http://ir.ia.ac.cn/handle/173211/58455]  
专题复杂系统管理与控制国家重点实验室_深度强化学习
通讯作者Zhang, Qichao
作者单位1.Chinese Acad Sci, Inst Automat, Key Lab Multimodal Artificial Intelligence Syst, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Univ Hong Kong, Hong Kong 100085, Peoples R China
4.Huawei Technol, Noahs Ark Lab, Beijing 100085, Peoples R China
5.Tianjin Univ, Coll Intelligence & Comp, Tianjin 300350, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Junjie,Zhang, Qichao,Mu, Yao,et al. Prototypical Context-Aware Dynamics for Generalization in Visual Control With Model-Based Reinforcement Learning[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2024:11.
APA Wang, Junjie.,Zhang, Qichao.,Mu, Yao.,Li, Dong.,Zhao, Dongbin.,...&Hao, Jianye.(2024).Prototypical Context-Aware Dynamics for Generalization in Visual Control With Model-Based Reinforcement Learning.IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,11.
MLA Wang, Junjie,et al."Prototypical Context-Aware Dynamics for Generalization in Visual Control With Model-Based Reinforcement Learning".IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2024):11.

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。