Past talk · AI/ML Seminar Series
CrystalBox: Future-Based Explanations for Deep RL Network Controllers
Assistant Professor of Computer Science, University of California, Irvine
- Date & time
- Monday, June 5, 2023 · 1:00 PM
- Location
- Donald Bren Hall 4011
Abstract
Lack of explainability is a key factor limiting the practical adoption of high-performant Deep Reinforcement Learning (DRL) controllers in systems environments. Explainable RL for networking hitherto used salient input features to interpret a controller's behavior. However, these feature-based solutions do not completely explain the controller's decision-making process. In this talk, I will present CrystalBox, a framework that explains a controller's behavior in terms of the future impact on key network performance metrics. CrystalBox employs a novel learning-based approach to generate succinct and expressive explanations, using reward components of the DRL controller as the basis. I will present three practical use cases: cross-state explainability, guided reward design, and network observability.
About the speaker
Sangeetha Abdu Jyothi is an Assistant Professor in the Computer Science department at the University of California, Irvine. Her research interests lie at the intersection of computer systems, networking, and machine learning. She completed her Ph.D. at the University of Illinois, Urbana-Champaign in 2019 and leads the Networking, Systems, and AI Lab (NetSAIL) at UCI.