Infinite time horizon safety of Bayesian neural networks

• Main Authors: LECHNER, Mathias, ZIKELIC, Dorde, CHATTERJEE, Krishnendu, HENZINGER, Thomas A.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: OS and Networks
• Online Access: https://ink.library.smu.edu.sg/sis_research/9066; https://ink.library.smu.edu.sg/context/sis_research/article/10069/viewcontent/NeurIPS_2021_infinite_time_horizon_safety_of_bayesian_neural_networks_Paper.pdf
• Institution: Singapore Management University

Bayesian neural networks (BNNs) place distributions over the weights of a neural network to model uncertainty in the data and the network’s prediction. We consider the problem of verifying safety when running a Bayesian neural network policy in a feedback loop with infinite time horizon systems. Compared to the existing sampling-based approaches, which are inapplicable to the infinite time horizon setting, we train a separate deterministic neural network that serves as an infinite time horizon safety certificate. In particular, we show that the certificate network guarantees the safety of the system over a subset of the BNN weight posterior’s support. Our method first computes a safe weight set and then alters the BNN’s weight posterior to reject samples outside this set. Moreover, we show how to extend our approach to a safe-exploration reinforcement learning setting, in order to avoid unsafe trajectories during the training of the policy. We evaluate our approach on a series of reinforcement learning benchmarks, including non-Lyapunovian safety specifications.