Offline Meta-Reinforcement Learning for Industrial Insertion
Tony Z. Zhao(Stanford University), Sergey Levine(University of California, Berkeley), Jianlan Luo(University of California, Berkeley), Oleg Sushkov(Google DeepMind (United Kingdom)), Nicolas Heess(Google DeepMind (United Kingdom)), Jon Scholz(Google DeepMind (United Kingdom)), Rugile Pevceviciute(Google DeepMind (United Kingdom)), Stefan Schaal(Google (United States))
2022 International Conference on Robotics and Automation (ICRA)
May 23, 2022
Cited by 67
Related Papers
Deterministic policy gradient algorithms
|HAL (Le Centre pour la Communication Scientifique Directe)|2014|1.7k
Emergence of Locomotion Behaviours in Rich Environments
|arXiv (Cornell University)|2017|669
Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
|arXiv (Cornell University)|2017|510
Graph networks as learnable physics engines for inference and control
|arXiv (Cornell University)|2018|280
Learning an Embedding Space for Transferable Robot Skills
|International Conference on Learning Representations|2018|190