Safe Exploration via Policy Priors

Manuel Wendl, Yarden As, Manish Prajapat, Anton Pollak, Stelian Coros, Andreas Krause

Track: Research Track

Keywords: Safe Exploration, Deep Reinfrocement Learning, Safe RL, Constrained Markov Decision Process

Abstract: Safe exploration is a key requirement for reinforcement learning agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this work, we tackle this challenge by utilizing suboptimal yet conservative policies (e.g., obtained from offline data or simulators) as priors. Our approach, SOOPER, uses probabilistic dynamics models to optimistically explore, yet pessimistically fall back to the conservative policy prior if needed. We prove that SOOPER guarantees safety throughout learning, and establish convergence to an optimal policy by bounding its cumulative regret. Extensive experiments on key safe RL benchmarks and real-world hardware demonstrate that SOOPER is scalable, outperforms the state-of-the-art and validate our theoretical guarantees in practice.

Submission Number: 61