Boosting Verification of Deep Reinforcement Learning via Piece-Wise Linear Decision Neural Networks

Published: 21 Sept 2023, Last Modified: 21 Dec 2023NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: Deep reinforcement learning, Reachability analysis, Hybrid system, State abstraction
TL;DR: We propose a novel DNN-based piece-wise linear decision model to facilitate the verification of DRL systems while achieving the comparable performance as ordinary DNN.
Abstract: Formally verifying deep reinforcement learning (DRL) systems suffers from both inaccurate verification results and limited scalability. The major obstacle lies in the large overestimation introduced inherently during training and then transforming the inexplicable decision-making models, i.e., deep neural networks (DNNs), into easy-to-verify models. In this paper, we propose an inverse transform-then-train approach, which first encodes a DNN into an equivalent set of efficiently and tightly verifiable linear control policies and then optimizes them via reinforcement learning. We accompany our inverse approach with a novel neural network model called piece-wise linear decision neural networks (PLDNNs), which are compatible with most existing DRL training algorithms with comparable performance against conventional DNNs. Our extensive experiments show that, compared to DNN-based DRL systems, PLDNN-based systems can be more efficiently and tightly verified with up to $438$ times speedup and a significant reduction in overestimation. In particular, even a complex $12$-dimensional DRL system is efficiently verified with up to 7 times deeper computation steps.
Supplementary Material: zip
Submission Number: 11232