Keywords: Bayesian neural networks, BNN, safety verification
Abstract: 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.
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
TL;DR: Verification of Bayesian neural networks in a feedback loop with infinite time horizon systems
Supplementary Material: pdf
Code: https://github.com/mlech26l/bayesian_nn_safety
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/infinite-time-horizon-safety-of-bayesian/code)
9 Replies
Loading