Self-Supervised Imitation for Offline Reinforcement Learning With Hindsight Relabeling-Reference-Cited by-同舟云学术

Self-Supervised Imitation for Offline Reinforcement Learning With Hindsight Relabeling

Author:

Yu Xudong¹^ORCID,Bai Chenjia²^ORCID,Wang Changhong¹^ORCID,Yu Dengxiu³^ORCID,Chen C. L. Philip⁴^ORCID,Wang Zhen⁵^ORCID

Affiliation:

1. Space Control and Inertial Technology Research Center, Harbin Institute of Technology, Harbin, China

2. Fundamental Theory, Shanghai Artificial Intelligence Laboratory, Shanghai, China

3. Unmanned System Research Institute, Northwestern Polytechnical University, Xi’an, China

4. School of Computer Science and Engineering, South China University of Technology, Guangzhou, China

5. School of Artificial Intelligence, Optics and Electronics and the School of Cyberspace, Northwestern Polytechnical University, Xi’an, China

Funder

National Science Fund for Distinguished Young Scholars

Heilongjiang Touyan Innovation Team Program

National Natural Science Foundation of China

Fok Ying Tong Education Foundation

Tencent Foundation and XPLORER PRIZE

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Computer Science Applications,Human-Computer Interaction,Control and Systems Engineering,Software

Link

Reference58 articles.

2. Counterfactual credit assignment in model-free reinforcement learning;mesnard;Proc Int Conf Mach Learn,2021

4. Dynamic bottleneck for robust self-supervised exploration;bai;Proc Adv Neural Inf Process Syst,2021

5. PLAS: Latent action space for offline reinforcement learning;zhou;Proc Conf Robot Learn,2021

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献