{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:08:41Z","timestamp":1771330121048,"version":"3.50.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>A longstanding objective in classical planning is to synthesize policies that generalize across multiple problems from the same domain. In this work, we study generalized policy search-based methods with a focus on the score function used to guide the search over policies. We demonstrate limitations of two score functions --- policy evaluation and plan comparison --- and propose a new approach that overcomes these limitations. The main idea behind our approach, Policy-Guided Planning for Generalized Policy Generalization (PG3), is that a candidate policy should be used to guide planning on training problems as a mechanism for evaluating that candidate. Theoretical results in a simplified setting give conditions under which PG3 is optimal or admissible. We then study a specific instantiation of policy search where planning problems are PDDL-based and policies are lifted decision lists. Empirical results in six domains confirm that PG3 learns generalized policies more efficiently and effectively than several baselines.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/650","type":"proceedings-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T02:55:56Z","timestamp":1657940156000},"page":"4686-4692","source":"Crossref","is-referenced-by-count":1,"title":["PG3: Policy-Guided Planning for Generalized Policy Generation"],"prefix":"10.24963","author":[{"given":"Ryan","family":"Yang","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Silver","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aidan","family":"Curtis","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomas","family":"Lozano-Perez","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leslie","family":"Kaelbling","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","theme":"Artificial Intelligence","location":"Vienna, Austria","acronym":"IJCAI-2022","number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2022,7,23]]},"end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:10:54Z","timestamp":1658142654000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/650"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/650","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}