{"type":"ScholarlyArticle","title":"Counterfactual Strategies for Markov Decision Processes","authors":[{"name":"Paul Kobialka","slug":"paul-kobialka","given":"Paul","family":"Kobialka","affiliation":""},{"name":"Lina Gerlach","slug":"lina-gerlach","given":"Lina","family":"Gerlach","affiliation":""},{"name":"Francesco Leofante","slug":"francesco-leofante","given":"Francesco","family":"Leofante","affiliation":""},{"name":"Erika Ábrahám","slug":"erika-abraham","given":"Erika","family":"Ábráham","affiliation":""},{"name":"Silvia Lizeth Tapia Tarifa","slug":"silvia-lizeth-tapia-tarifa","given":"Silvia Lizeth","family":"Tapia Tarifa","affiliation":""},{"name":"Einar Broch Johnsen","slug":"einar-broch-johnsen","given":"Einar Broch","family":"Johnsen","affiliation":""}],"abstract":"Counterfactuals are widely used in AI to explain how minimal changes to a model’s input can lead to a different output. \r\nHowever, established methods for computing counterfactuals typically focus on one-step decision-making, and are not directly applicable to sequential decision-making tasks. \r\nThis paper fills this gap by introducing counterfactual strategies for Markov Decision Processes (MDPs). \r\nDuring MDP execution, a strategy decides which of the enabled actions (with known probabilistic effects) to execute next. \r\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. \r\nWe encode such counterfactual strategies as solutions to non-linear optimization problems, and further extend our encoding to synthesize diverse counterfactual strategies. \r\nWe evaluate our approach on four real-world datasets and demonstrate its practical viability in sophisticated sequential decision-making tasks.","doi":"10.24963/ijcai.2025/47","url":"https://ijcai.org/proceedings/2025/47","pdf":"https://ijcai.org/proceedings/2025/0047.pdf","markdown":"https://ijcai.org/proceedings/2025/47.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/47","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":47,"pages":{"first":412,"last":420},"keywords":["Planning and Scheduling: PS: Markov decisions processes","AI Ethics, Trust, Fairness: ETF: Explainability and interpretability"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}