Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations
This addresses safety concerns for deploying RL in real-world applications, offering a method that eliminates training-time violations, which is a significant improvement over existing approaches.
The paper tackles the problem of training-time safety violations in reinforcement learning by proposing an algorithm that achieves zero violations while learning high-reward policies, even in environments where such policies must operate near safety boundaries. Empirical results show that prior methods require hundreds of violations for decent rewards, whereas their algorithm incurs zero violations.
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.