{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:38:08Z","timestamp":1761176288609,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"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":[[2025,10,21]]},"abstract":"<jats:p>Recent work has introduced methodology for testing learned action policies in AI Planning, aiming to effectively identify bug states where policy behavior is sub-optimal. While this work focused on cost-optimality in classical planning, here we apply the core ideas to safety testing in planning with initial-state and action-outcome non-determinism. We cover the entire testing pipeline, introducing fuzzing algorithms to find unsafe policy runs, as well as test oracles to identify bugs where such unsafe behavior could be avoided. Going beyond the previous framework, we introduce a final step to the pipeline, identifying faults which we define to be specific policy decisions \u2013 state\/action pairs \u2013 transitioning from a safe state (where a safe policy exists) to an unsafe state (where no such policy exists). We adapt a range of known algorithms for these purposes, including also approximate ones bounding the number of times we are allowed to diverge from the learned policy. We run comprehensive experiments evaluating each part of our pipeline. Key takeaways are that safety testing can be quite cheap, in contrast to cost-optimality testing; and that variants of Tarjan\u2019s algorithm tend to be highly effective for this purpose.<\/jats:p>","DOI":"10.3233\/faia251388","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:00:15Z","timestamp":1761127215000},"source":"Crossref","is-referenced-by-count":0,"title":["Policy Safety Testing in Non-Deterministic Planning: Fuzzing, Test Oracles, Fault Analysis"],"prefix":"10.3233","author":[{"given":"Chaahat","family":"Jain","sequence":"first","affiliation":[{"name":"Saarland University, Saarland Informatics Campus, Germany"}]},{"given":"Daniel","family":"Sherbakov","sequence":"additional","affiliation":[{"name":"Saarland University, Saarland Informatics Campus, Germany"}]},{"given":"Marcel","family":"Vinzent","sequence":"additional","affiliation":[{"name":"Saarland University, Saarland Informatics Campus, Germany"}]},{"given":"Marcel","family":"Steinmetz","sequence":"additional","affiliation":[{"name":"LAAS-CNRS, Toulouse, France"}]},{"given":"Jesse","family":"Davis","sequence":"additional","affiliation":[{"name":"Department of Computer Science, KU Leuven, Leuven, Belgium"}]},{"given":"J\u00f6rg","family":"Hoffmann","sequence":"additional","affiliation":[{"name":"Saarland University, Saarland Informatics Campus, Germany"},{"name":"German Research Center for Artificial Intelligence (DFKI), Saarbr\u00fccken, Germany"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:00:16Z","timestamp":1761127216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251388"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251388","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}