Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones

10/29/2020
by   Brijen Thananjeyan, et al.
15

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 data to learn about constraint violating zones before policy learning and (2) separating the goals of improving task performance and constraint satisfaction across two policies: a task policy that only optimizes the task reward and a recovery policy that guides the agent to safety when constraint violation is likely. We evaluate Recovery RL on 6 simulation domains, including two contact-rich manipulation tasks and an image-based navigation task, and an image-based obstacle avoidance task on a physical robot. We compare Recovery RL to 5 prior safe RL methods which jointly optimize for task performance and safety via constrained optimization or reward shaping and find that Recovery RL outperforms the next best prior method across all domains. Results suggest that Recovery RL trades off constraint violations and task successes 2 - 80 times more efficiently in simulation domains and 3 times more efficiently in physical experiments. See https://tinyurl.com/rl-recovery for videos and supplementary material.

READ FULL TEXT

page 1

page 3

page 6

page 13

page 14

research
07/27/2022

A Contact-Safe Reinforcement Learning Framework for Contact-Rich Robot Manipulation

Reinforcement learning shows great potential to solve complex contact-ri...
research
09/21/2023

Learning to Recover for Safe Reinforcement Learning

Safety controllers is widely used to achieve safe reinforcement learning...
research
07/10/2021

LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks

Reinforcement learning (RL) algorithms have shown impressive success in ...
research
12/07/2021

MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance

Safe exploration is critical for using reinforcement learning (RL) in ri...
research
01/05/2023

Reinforcement Learning-Based Air Traffic Deconfliction

Remain Well Clear, keeping the aircraft away from hazards by the appropr...
research
10/27/2020

Conservative Safety Critics for Exploration

Safe exploration presents a major challenge in reinforcement learning (R...
research
09/29/2021

Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning

One of the key challenges to deep reinforcement learning (deep RL) is to...

Please sign up or login with your details

Forgot password? Click here to reset