{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:45Z","timestamp":1758672885517,"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>Counterfactuals are widely used in AI to explain how minimal changes to a model\u2019s input can lead to a different output. \n\nHowever, established methods for computing counterfactuals typically focus on one-step decision-making, and are not directly applicable to sequential decision-making tasks. \n\nThis paper fills this gap by introducing counterfactual strategies for Markov Decision Processes (MDPs). \n\nDuring MDP execution, a strategy decides which of the enabled actions (with known probabilistic effects) to execute next. \n\nGiven an initial strategy that reaches an undesired outcome with a probability above some limit, we identify minimal changes to the initial strategy to reduce that probability below the limit. \n\nWe encode such counterfactual strategies as solutions to non-linear optimization problems, and further extend our encoding to synthesize diverse counterfactual strategies. \n\nWe evaluate our approach on four real-world datasets and demonstrate its practical viability in sophisticated sequential decision-making tasks.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/47","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"412-420","source":"Crossref","is-referenced-by-count":0,"title":["Counterfactual Strategies for Markov Decision Processes"],"prefix":"10.24963","author":[{"given":"Paul","family":"Kobialka","sequence":"first","affiliation":[{"name":"University of Oslo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lina","family":"Gerlach","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Leofante","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erika","family":"\u00c1brah\u00e1m","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silvia Lizeth","family":"Tapia Tarifa","sequence":"additional","affiliation":[{"name":"University of Oslo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Einar Broch","family":"Johnsen","sequence":"additional","affiliation":[{"name":"University of Oslo"}],"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":"2025-09-23T11:32:41Z","timestamp":1758627161000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/47"}},"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\/47","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}