[북마크] Learning to be Safe: Deep RL with a Safety Critic (Krishnan Srinivasan, arXiv 2020)

2021. 3. 8. 15:45

Author : Krishnan Srinivasan, Benjamin Eysenbach, Sehoon Ha, Jie Tan, Chelsea Finn
Paper Link : arxiv.org/abs/2010.14603

[북마크] Safe Reinforcement Learning for Legged Locomotion (Tsung-Yen Yang, ArXiv 2022) (0)	2022.05.10
[요약] Learning robust perceptive locomotion for quadrupedal robots in the wild (Takahiro Miki, Science Robotics 2022) (0)	2022.02.10
[요약] RMA: Rapid Motor Adaptation for Legged Robot (Ashish Kumar, RSS 2021) (0)	2021.07.14
[북마크] Conservative Safety Critics for Exploration (Homanga Bharadhwaj, ICLR 2021) (0)	2020.10.29
[정리] Learning to Walk in the Real World with Minimal Human Effort (Sehoon Ha, 2020) (0)	2020.06.06

AI & Medicine