Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations
arXiv:2108.01846
Abstract
Training-time safety violations have been a major concern when we deploy reinforcement learning algorithms in the real world. This paper explores the possibility of safe RL algorithms with zero training-time safety violations in the challenging setting where we are only given a safe but trivial-reward initial policy without any prior knowledge of the dynamics model and additional offline data. We propose an algorithm, Co-trained Barrier Certificate for Safe RL (CRABS), which iteratively learns barrier certificates, dynamics models, and policies. The barrier certificates, learned via adversarial training, ensure the policy's safety assuming calibrated learned dynamics model. We also add a regularization term to encourage larger certified regions to enable better exploration. Empirical simulations show that zero safety violations are already challenging for a suite of simple environments with only 2-4 dimensional state space, especially if high-reward policies have to visit regions near the safety boundary. Prior methods require hundreds of violations to achieve decent rewards on these tasks, whereas our proposed algorithms incur zero violations.
NeurIPS 2021. Source code at https://github.com/roosephu/crabs
References in corpus (9)
- Searching for Activation Functions
- Solving Rubik's Cube with a Robot Hand
- Safe Exploration in Continuous Action Spaces
- Lyapunov-based Safe Policy Optimization for Continuous Control
- Learning to be Safe: Deep RL with a Safety Critic
- Individual Calibration with Randomized Forecasting
- Neurosymbolic Reinforcement Learning with Formally Verified Exploration
- Enforcing robust control guarantees within neural network policies
- Lyapunov Barrier Policy Optimization