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||American 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.|
|Number of pages||11|
|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
|Name||Proceedings of the 21st Formal Methods in Computer-Aided Design, FMCAD 2021|
|Conference||21st International Conference on Formal Methods in Computer-Aided Design, FMCAD 2021|
|Period||18/10/21 → 22/10/21|
Bibliographical noteFunding Information:
Acknowledgements. We thank Nathan Jay, Tomer Eliyahu and the anonymous reviewers for their contributions to this project. The project was partially supported by the Israel Science Foundation (grant number 683/18), the Binational Science Foundation (grant numbers 2017662 and 2019798), and the Center for Interdisciplinary Data Science Research at The Hebrew University of Jerusalem.
© 2021 FMCAD Associ.