Counterfactual strategies for Markov decision processes
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
Counterfactuals are widely used in AI to explain how minimal changes to a model’s input can lead to a different output. However, established methods for computing counterfactuals typically focus on one-step decision-making, and are not directly applicable to sequential decision-making tasks. This paper fills this gap by introducing counterfactual strategies for Markov Decision Processes (MDPs). During MDP execution, a strategy decides which of the enabled actions (with known probabilistic effects) to execute next. Given 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. We encode such counterfactual strategies as solutions to non-linear optimization problems, and further extend our encoding to synthesize diverse counterfactual strategies. We evaluate our approach on four real-world datasets and demonstrate its practical viability in sophisticated sequential decision-making tasks.
Date Issued
2025-08-01
Date Acceptance
2025-04-29
Citation
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025, pp.412-420
Publisher
IJCAI Organization
Start Page
412
End Page
420
Journal / Book Title
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence
Copyright Statement
© 2025 IJCAI Organisation.
Source
International Joint Conference on Artificial Intelligence (IJCAI) 2025
Publication Status
Published
Start Date
2025-08-16
Finish Date
2025-08-22
Coverage Spatial
Montreal, Canada