Attribution-based Explanations for Markov Decision Processes
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 652-660.
https://doi.org/10.24963/ijcai.2026/74
Keywords
- Uncertainty in AI: Sequential decision making
- AI Ethics, Trust, Fairnes: Explainability and interpretability
Abstract
Attribution techniques explain the outcome of an AI model by assigning a numerical score to its inputs. So far, these techniques have mainly focused on attributing importance to static input features at a single point in time, and thus fail to generalize to sequential decision-making settings. This paper fills this gap by introducing techniques to generate attribution-based explanations for Markov Decision Processes (MDPs). We give a formal characterization of what attributions should represent in MDPs, focusing on explanations that assign importance scores to both individual states and execution paths. We show how importance scores can be computed by leveraging techniques for strategy synthesis, enabling the efficient computation of these scores despite the non-determinism inherent in an MDP. We evaluate our approach on five case-studies, demonstrating its utility in providing interpretable insights into the logic of sequential decision-making agents.
@inproceedings{ijcai2026p74,
title = {Attribution-based Explanations for Markov Decision Processes},
author = {Kobialka, Paul and Pferscher, Andrea and Leofante, Francesco and Ábráham, Erika and Tapia Tarifa, Silvia Lizeth and Johnsen, Einar Broch},
booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-26}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Diego Calvanese},
pages = {652--660},
year = {2026},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2026/74},
url = {https://doi.org/10.24963/ijcai.2026/74},
}
TY - CPAPER TI - Attribution-based Explanations for Markov Decision Processes AU - Kobialka, Paul AU - Pferscher, Andrea AU - Leofante, Francesco AU - Ábráham, Erika AU - Tapia Tarifa, Silvia Lizeth AU - Johnsen, Einar Broch T2 - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2026 SP - 652 EP - 660 DO - 10.24963/ijcai.2026/74 UR - https://doi.org/10.24963/ijcai.2026/74 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: