Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates

arXiv:2405.14058v1 Announce Type: cross
Abstract: Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating agents that control autonomous systems. However, the "black box" nature of DRL agents limits their deployment in real-world safety-critical applications. A promising approach for providing strong guarantees on an agent's behavior is to use Neural Lyapunov Barrier (NLB) certificates, which are learned functions over the system whose properties indirectly imply that an agent behaves as desired. However, NLB-based certificates are typically difficult to …

abstract agent agents applications arxiv autonomous autonomous systems behavior black box box control cs.ai cs.lg cs.sy deployment eess.sy however machine machine learning nature paradigm reinforcement reinforcement learning safety safety-critical systems type world