Constrained Variational Policy Optimization for Safe Reinforcement Learning

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality guarantees. This paper overcomes the issues from the perspective of...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-06
Main Authors: Liu, Zuxin, Cen, Zhepeng, Isenbaev, Vladislav, Liu, Wei, Wu, Zhiwei Steven, Li, Bo, Zhao, Ding
Format: Article
Language:English
Subjects:
Constraints
Convexity
Machine learning
Optimization
Probabilistic inference
Safety critical
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality guarantees. This paper overcomes the issues from the perspective of probabilistic inference. We introduce a novel Expectation-Maximization approach to naturally incorporate constraints during the policy learning: 1) a provable optimal non-parametric variational distribution could be computed in closed form after a convex optimization (E-step); 2) the policy parameter is improved within the trust region based on the optimal variational distribution (M-step). The proposed algorithm decomposes the safe RL problem into a convex optimization phase and a supervised learning phase, which yields a more stable training performance. A wide range of experiments on continuous robotic tasks shows that the proposed method achieves significantly better constraint satisfaction performance and better sample efficiency than baselines. The code is available at https://github.com/liuzuxin/cvpo-safe-rl.
ISSN:2331-8422