Attribution-based Explanations for Markov Decision Processes

Kobialka, Paul; Pferscher, Andrea; Leofante, Francesco; Ábráham, Erika; Tapia Tarifa, Silvia Lizeth; Johnsen, Einar Broch

doi:10.24963/ijcai.2026/74

Attribution-based Explanations for Markov Decision Processes

Paul Kobialka, Andrea Pferscher, Francesco Leofante, Erika Ábrahám, Silvia Lizeth Tapia Tarifa, Einar Broch Johnsen

Download BibTeX Cite

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.

Paul Kobialka, Andrea Pferscher, Francesco Leofante, Erika Ábráham, Silvia Lizeth Tapia Tarifa, and Einar Broch Johnsen. 2026. Attribution-based Explanations for Markov Decision Processes. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 652–660. https://doi.org/10.24963/ijcai.2026/74

@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  -