{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:49:27Z","timestamp":1782989367068,"version":"3.54.5"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686707","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,2]]},"abstract":"<jats:p>We introduce State Vector Space Partitioning (SVSP), a novel method to mimic a black-box reinforcement learning policy using a set of human-interpretable sub-policies. By partitioning a distillation dataset of state\u2013action pairs with linear support vector machine splits, SVSP constructs a compact and structured representation of the original policy where linear models can be interpreted as a measure of feature importance. Our method improves mean return by +7.4% over previous critic-driven state partitioning attempts such as Voronoi State Partitioning (VSP) and +2.8% over the original TD3 policy, while reducing the number of required sub-policies against VSP by 82.1%. Our results pave the path towards a more flexible form of distillation where both the decision boundary and surrogate models can be chosen within a margin of the original black box behavior.<\/jats:p>","DOI":"10.3233\/faia260549","type":"book-chapter","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T09:58:10Z","timestamp":1782986290000},"source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies"],"prefix":"10.3233","author":[{"given":"Senne","family":"Deproost","sequence":"first","affiliation":[{"name":"Vrije Universiteit Brussel"},{"name":"Flanders Make"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehrdad","family":"Asadi","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Brussel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Brussel"},{"name":"Flanders Make"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","HHAI 2026"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA260549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T09:58:10Z","timestamp":1782986290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA260549"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"ISBN":["9781643686707"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia260549","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]}}}