Solving Robotic Manipulation With Sparse Reward Reinforcement Learning Via Graph-Based Diversity and Proximity-Reference-Cited by-同舟云学术

Solving Robotic Manipulation With Sparse Reward Reinforcement Learning Via Graph-Based Diversity and Proximity

Author:

Bing Zhenshan¹^ORCID,Zhou Hongkuan¹^ORCID,Li Rui²^ORCID,Su Xiaojie²^ORCID,Morin Fabrice O.¹^ORCID,Huang Kai³^ORCID,Knoll Alois¹^ORCID

Affiliation:

1. Department of Informatics, Technical University of Munich, Munich, Germany

2. School of Automation, Chongqing University, Chongqing, China

3. School of Computer Science, Sun Yat-sen University, Guangzhou, China

Funder

H2020 Future and Emerging Technologies

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Control and Systems Engineering

Link

Reference27 articles.

1. Exploration via hindsight goal generation;ren;Proc 33rd Conf Neural Inf Process Syst,0

3. Prioritized experience replay;schaul;Proc Int Conf Learn Representations,0

4. Maximum entropy-regularized multi-goal reinforcement learning;zhao;Proc 36th Int Conf Mach Learn,0

5. Energy-based hindsight experience prioritization;zhao;Proc 2nd Conf Robot Learn,0

Cited by 21 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

5. Contact Energy Based Hindsight Experience Prioritization;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13