Safe Reinforcement Learning in Constrained Markov Decision Processes

Abstract

Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision processes under unknown safety constraints. Specifically, we take a stepwise approach for optimizing safety and cumulative reward. In our method, the agent first learns safety constraints by expanding the safe region, and then optimizes the cumulative reward in the certified safe region. We provide theoretical guarantees on both the satisfaction of the safety constraint and the near-optimality of the cumulative reward under proper regularity assumptions. In our experiments, we demonstrate the effectiveness of SNO-MDP through two experiments: one uses a synthetic data in a new, openly-available environment named GP-SAFETY-GYM, and the other simulates Mars surface exploration by using real observation data.

10 pages, 6 figures, Accepted to ICML2020

Cited by in corpus (10)

• Provably Efficient Safe Exploration via Primal-Dual Policy Optimization
• Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method
• Context-Aware Safe Reinforcement Learning for Non-Stationary Environments
• Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents
• Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning
• GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model
• Safe Exploration by Solving Early Terminated MDP
• Safe Reinforcement Learning with Linear Function Approximation
• Learning to Be Cautious
• Safety aware model-based reinforcement learning for optimal control of a class of output-feedback nonlinear systems