Abstract
Deep neural networks (DNNs) have gained significant popularity in recent years, becoming the state of the art in a variety of domains. In particular, deep reinforcement learning (DRL) has recently been employed to train DNNs that realize control policies for various types of real-world systems. In this work, we present the whiRL 2.0 tool, which implements a new approach for verifying complex properties of interest for DRL systems. To demonstrate the benefits of whiRL 2.0, we apply it to case studies from the communication networks domain that have recently been used to motivate formal verification of DRL systems, and which exhibit characteristics that are conducive for scalable verification. We propose techniques for performing k-induction and semi-automated invariant inference on such systems, and leverage these techniques for proving safety and liveness properties that were previously impossible to verify due to the scalability barriers of prior approaches. Furthermore, we show how our proposed techniques provide insights into the inner workings and the generalizability of DRL systems. whiRL 2.0 is publicly available online.
Original language | English |
---|---|
Title of host publication | Proceedings of the 21st Formal Methods in Computer-Aided Design, FMCAD 2021 |
Editors | Ruzica Piskac, Michael W. Whalen, Warren A. Hunt, Georg Weissenbacher |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 193-203 |
Number of pages | 11 |
ISBN (Electronic) | 9783854480464 |
DOIs | |
State | Published - 2021 |
Event | 21st International Conference on Formal Methods in Computer-Aided Design, FMCAD 2021 - Virtual, Online, United States Duration: 18 Oct 2021 → 22 Oct 2021 |
Publication series
Name | Proceedings of the 21st Formal Methods in Computer-Aided Design, FMCAD 2021 |
---|
Conference
Conference | 21st International Conference on Formal Methods in Computer-Aided Design, FMCAD 2021 |
---|---|
Country/Territory | United States |
City | Virtual, Online |
Period | 18/10/21 → 22/10/21 |
Bibliographical note
Publisher Copyright:© 2021 FMCAD Associ.