Boosting verification of deep reinforcement learning via piece-wise linear decision neural networks
Formally verifying deep reinforcement learning (DRL) systems suffers from both inaccurate
verification results and limited scalability. The major obstacle lies in the large overestimation …
verification results and limited scalability. The major obstacle lies in the large overestimation …
Stochastic omega-regular verification and control with supermartingales
A Abate, M Giacobbe, D Roy - International Conference on Computer …, 2024 - Springer
We present for the first time a supermartingale certificate for ω-regular specifications. We
leverage the Robbins & Siegmund convergence theorem to characterize supermartingale …
leverage the Robbins & Siegmund convergence theorem to characterize supermartingale …
Safe Exploration in Reinforcement Learning by Reachability Analysis over Learned Models
We introduce VELM, a reinforcement learning (RL) framework grounded in verification
principles for safe exploration in unknown environments. VELM ensures that an RL agent …
principles for safe exploration in unknown environments. VELM ensures that an RL agent …