{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T12:45:38Z","timestamp":1756385138557},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"13","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1609\/aaai.v38i13.29372","type":"journal-article","created":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T11:18:41Z","timestamp":1711365521000},"page":"14563-14571","source":"Crossref","is-referenced-by-count":1,"title":["CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems"],"prefix":"10.1609","volume":"38","author":[{"given":"Sagar","family":"Patel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangeetha","family":"Abdu Jyothi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nina","family":"Narodytska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2024,3,24]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/29372\/30590","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/29372\/30591","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/29372\/30590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T11:18:42Z","timestamp":1711365522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/29372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,24]]},"references-count":0,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2024,3,25]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v38i13.29372","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2024,3,24]]}}}