{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:50Z","timestamp":1758672890210,"version":"3.44.0"},"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":[[2025,9]]},"abstract":"<jats:p>To apply reinforcement learning to safety-critical applications, we ought to provide safety guarantees during both policy training and deployment. In this work we present novel theoretical results that provide a bound on the probability of violating a safety property for a new task-specific policy in a model-free, episodic setup: the bound, based on a 'maximum policy ratio' that is computed with respect to a 'safe' base policy, can also be more generally applied to temporally-extended properties (beyond safety) and to robust control problems. We thus present SPoRt, which also provides a data-driven approach for obtaining such a bound for the base policy, based on scenario theory, and which includes Projected PPO, a new projection-based approach for training the task-specific policy while maintaining a user-specified bound on property violation. Hence, SPoRt enables the user to trade off safety guarantees in exchange for task-specific performance. Accordingly, we present experimental results demonstrating this trade-off, as well as a comparison of the theoretical bound to posterior bounds based on empirical violation rates.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/554","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"4976-4984","source":"Crossref","is-referenced-by-count":0,"title":["SPoRt - Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL"],"prefix":"10.24963","author":[{"given":"Jacques","family":"Cloete","sequence":"first","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaus","family":"Vertovec","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Abate","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:34:21Z","timestamp":1758627261000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/554"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/554","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}