Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions
This work addresses safety-critical exploration for reinforcement learning systems, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of ensuring safety during exploration in model-based reinforcement learning by introducing Lyapunov-like control barrier functions (LCBFs) to guarantee constraint adherence, and demonstrates through numerical examples that it handles more general safety constraints than existing methods.
This paper develops a model-based reinforcement learning (MBRL) framework for learning online the value function of an infinite-horizon optimal control problem while obeying safety constraints expressed as control barrier functions (CBFs). Our approach is facilitated by the development of a novel class of CBFs, termed Lyapunov-like CBFs (LCBFs), that retain the beneficial properties of CBFs for developing minimally-invasive safe control policies while also possessing desirable Lyapunov-like qualities such as positive semi-definiteness. We show how these LCBFs can be used to augment a learning-based control policy to guarantee safety and then leverage this approach to develop a safe exploration framework in a MBRL setting. We demonstrate that our approach can handle more general safety constraints than comparative methods via numerical examples.