Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones

• Published in: IEEE robotics and automation letters Vol. 6; no. 3; pp. 4915 - 4922
• Main Authors: Thananjeyan, Brijen, Balakrishna, Ashwin, Nair, Suraj, Luo, Michael, Srinivasan, Krishnan, Hwang, Minho, Gonzalez, Joseph E., Ibarz, Julian, Finn, Chelsea, Goldberg, Ken
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.07.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Constraints; Domains; Image manipulation; Learning; Navigation; Obstacle avoidance; Optimization; Recovery; Recovery zones; Reinforcement learning; Safety

Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm which navigates this tradeoff by (1) leveraging offline dat...