Lyapunov Barrier Policy Optimization

Abstract

Deploying Reinforcement Learning (RL) agents in the real-world require that the agents satisfy safety constraints. Current RL agents explore the environment without considering these constraints, which can lead to damage to the hardware or even other agents in the environment. We propose a new method, LBPO, that uses a Lyapunov-based barrier function to restrict the policy update to a safe set for each training iteration. Our method also allows the user to control the conservativeness of the agent with respect to the constraints in the environment. LBPO significantly outperforms state-of-the-art baselines in terms of the number of constraint violations during training while being competitive in terms of performance. Further, our analysis reveals that baselines like CPO and SDDPG rely mostly on backtracking to ensure safety rather than safe projection, which provides insight into why previous methods might not have effectively limit the number of constraint violations.

References in corpus (11)

• Trust Region Policy Optimization
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• Solving Rubik's Cube with a Robot Hand
• Safe Model-based Reinforcement Learning with Stability Guarantees
• Safe Exploration in Continuous Action Spaces
• Lyapunov-based Safe Policy Optimization for Continuous Control
• Constrained Policy Optimization
• Algorithms for CVaR Optimization in MDPs
• Worst Cases Policy Gradients
• Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
• Safe Exploration for Interactive Machine Learning

Cited by in corpus (5)

• Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk
• Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations
• Safe Driving via Expert Guided Policy Optimization
• Safe Exploration by Solving Early Terminated MDP
• Learning Off-Policy with Online Planning