Causal Explainable Reinforcement Learning for Adaptive Question Selection in Human–AI Decision Systems

This study proposes Causal Explainable Reinforcement Learning for Adaptive Question Selection (CERL-AQS) to address the limitations of association-based explanation in adaptive AI. By integrating causal question value and counterfactual reasoning into RL, the framework seeks to explain not only why a question was asked, but also what would have happened without its information. Future research will focus on real-world human–AI experiments, automated causal-graph discovery, uncertainty-aware causal explanations, fairness-aware question selection, multimodal information acquisition, and scalable causal RL algorithms. Further work will also investigate online learning and deployment under distribution shift. These directions can advance CERL-AQS toward reliable, transparent, and practically deployable human-centered AI decision systems.

Amitai, Y., Septon, Y., & Amir, O. (2024). Explaining reinforcement learning agents through counterfactual action outcomes. Proceedings of the AAAI Conference on Artificial Intelligence, 38(9), 10003–10011. https://doi.org/10.1609/aaai.v38i9.28863 Bekkemoen, Y. (2024). Explainable reinforcement learning (XRL): A systematic literature review and taxonomy. Machine Learning, 113, 355–441. https://doi.org/10.1007/s10994-023-06479-7 Chen, H., Covert, I. C., Lundberg, S. M., & Lee, S.-I. (2023). Algorithms to estimate Shapley value feature attributions. Nature Machine Intelligence, 5, 590–601. https://doi.org/10.1038/s42256-023-00657-x Chou, Y.-L., Moreira, C., Bruza, P., Ouyang, C., & Jorge, J. (2022). Counterfactuals and causability in explainable artificial intelligence: Theory, algorithms, and applications. Information Fusion, 81, 59–83. https://doi.org/10.1016/j.inffus.2021.11.003 da Costa Cunha, C., Liu, W., French, T., & Mian, A. (2025). Unifying causal reinforcement learning: Survey, taxonomy, algorithms and applications [Preprint]. arXiv. https://arxiv.org/abs/2512.18135 Ganesan, V. et.al.,(2026a). Adaptive questioning as decision intelligence: A progressive disclosure framework for uncertainty-driven human–AI interaction. International Journal of Current Science, 16(1), 170–185. https://doi.org/10.56975/ijcsp.v16i1.303795  Jiang, J., Leofante, F., Rago, A., & Toni, F. (2024). Robust counterfactual explanations in machine learning: A survey. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 8086–8094. https://doi.org/10.24963/ijcai.2024/894 Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (Vol. 30, pp. 4765–4774). Madumal, P., Miller, T., Sonenberg, L., & Vetere, F. (2020). Explainable reinforcement learning through a causal lens. Proceedings of the AAAI Conference on Artificial Intelligence, 34(03), 2493–2500. https://doi.org/10.1609/aaai.v34i03.5631 Ganesan, V., et.al.,(2026b). Adaptive decision intelligence 2.0: Explainable, reinforcement learning-driven progressive questioning for autonomous human–AI decision systems. Journal of Emerging Trends and Novel Research, 4(3), JETNR2603144. https://doi.org/10.56975/jetnr.v4i3.233128 Pearl, J. (2009). Causality: Models, reasoning, and inference (2nd ed.). Cambridge University Press.