Reinforcement Learning with Ensemble Model Predictive Safety Certification

Reinforcement learning algorithms need exploration to learn. However, unsupervised exploration prevents the deployment of such algorithms on safety-critical tasks and limits real-world deployment. In this paper, we propose a new algorithm called Ensemble Model Predictive Safety Certification that combines model-based deep reinforcement learning with tube-based model predictive control to correct the actions taken by a learning agent, keeping safety constraint violations at a minimum through planning. Our approach aims to reduce the amount of prior knowledge about the actual system …

algorithm algorithms certification control cs.lg cs.ro deployment ensemble exploration learn paper predictive reinforcement reinforcement learning safety safety-critical tasks tube unsupervised world