CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems
Sagar Patel, Sangeetha Abdu Jyothi, Nina Narodytska
Abstract
We present CrystalBox, a novel, model-agnostic, posthoc explainability framework for Deep Reinforcement Learning (DRL) controllers in the large family of input-driven environments which includes computer systems. We combine the natural decomposability of reward functions in input-driven environments with the explanatory power of decomposed returns. We propose an efficient algorithm to generate future-based explanations across both discrete and continuous control environments. Using applications such as adaptive bitrate streaming and congestion control, we demonstrate CrystalBox's capability to generate high-fidelity explanations. We further illustrate its higher utility across three practical use cases: contrastive explanations, network observability, and guided reward design, as opposed to prior explainability techniques that identify salient features.
BibTeX
@article{Patel_Abdu Jyothi_Narodytska_2024, title={CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/29372}, DOI={10.1609/aaai.v38i13.29372}, abstractNote={We present CrystalBox, a novel, model-agnostic, posthoc explainability framework for Deep Reinforcement Learning (DRL) controllers in the large family of input-driven environments which includes computer systems. We combine the natural decomposability of reward functions in input-driven environments with the explanatory power of decomposed returns. We propose an efficient algorithm to generate future-based explanations across both discrete and continuous control environments. Using applications such as adaptive bitrate streaming and congestion control, we demonstrate CrystalBox’s capability to generate high-fidelity explanations. We further illustrate its higher utility across three practical use cases: contrastive explanations, network observability, and guided reward design, as opposed to prior explainability techniques that identify salient features.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Patel, Sagar and Abdu Jyothi, Sangeetha and Narodytska, Nina}, year={2024}, month={Mar.}, pages={14563-14571} }