Abstract
There has been growing interest in causal explanations of stochastic, sequential decision-making systems. Structural causal models and causal reasoning offer several theoretical benefits when exact inference can be applied. Furthermore, users overwhelmingly prefer the resulting causal explanations over other state-of-the-art systems. In this work, we focus on one such method, MeanRESP, and its approximate versions that drastically reduce compute load and assign a responsibility score to each variable, which helps identify smaller sets of causes to be used as explanations. However, this method, and its approximate versions in particular, lack deeper theoretical analysis and broader empirical tests. To address these shortcomings, we provide three primary contributions. First, we offer several theoretical insights on the sample complexity and error rate of approximate MeanRESP. Second, we discuss several automated metrics for comparing explanations generated from approximate methods to those generated via exact methods. While we recognize the significance of user studies as the gold standard for evaluating explanations, our aim is to leverage the proposed metrics to systematically compare explanation-generation methods along important quantitative dimensions. Finally, we provide a more detailed discussion of MeanRESP and how its output under different definitions of responsibility compares to existing widely adopted methods that use Shapley values.
S. Mahmud and S. B. Nashed—Authors contributed equally.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Allahyari, M., et al.: Text summarization techniques: a brief survey. arXiv preprint arXiv:1707.02268 (2017)
Bellman, R.: On the theory of dynamic programming. Natl. Acad. Sci. United States Am. 38(8), 716 (1952)
Bertossi, L., Li, J., Schleich, M., Suciu, D., Vagena, Z.: Causality-based explanation of classification outcomes (2020). arXiv preprint arXiv:2003.06868
Bertram, J., Wei, P.: Explainable deterministic MDPs (2018). arXiv preprint arXiv:1806.03492
Bertsekas, D.P.: Dynamic programming and optimal control (1995)
Brockman, G., et al.: OpenAI Gym (2016). https://arxiv.org/abs/1606.01540
Chen, J.Y., Lakhmani, S.G., Stowers, K., Selkowitz, A.R., Wright, J.L., Barnes, M.: Situation awareness-based agent transparency and human-autonomy teaming effectiveness. Theor. Issues Ergon. Sci. 19(3), 259–282 (2018)
Chockler, H., Halpern, J.Y.: Responsibility and blame: a structural-model approach. J. Artif. Intell. Res. 22, 93–115 (2004)
David Wong, E.: Understanding the generative capacity of analogies as a tool for explanation. J. Res. Sci. Teach. 30(10), 1259–1272 (1993)
Elizalde, F., Sucar, E., Noguez, J., Reyes, A.: Generating explanations based on markov decision processes. In: Aguirre, A.H., Borja, R.M., Garciá, C.A.R. (eds.) MICAI 2009. LNCS (LNAI), vol. 5845, pp. 51–62. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-05258-3_5
Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. Part I: Causes. Brit. J. Phil. Sci. 52(3), 613–622 (2005)
Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. Part II: explanations. Brit. J. Phil. Sci. 56(4), 889–911 (2005)
Hayes, B., Shah, J.A.: Improving robot controller transparency through autonomous policy explanation. In: ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 303–312 (2017)
Juozapaitis, Z., Koul, A., Fern, A., Erwig, M., Doshi-Velez, F.: Explainable reinforcement learning via reward decomposition. In: IJCAI/ECAI Workshop on Explainable Artificial Intelligence (2019)
Karimi, A.H., Schölkopf, B., Valera, I.: Algorithmic recourse: from counterfactual explanations to interventions. In: Proceedings of the ACM Conference on Fairness, Accountability, and Transparency, pp. 353–362 (2021)
Khan, O., Poupart, P., Black, J.: Minimal sufficient explanations for factored Markov decision processes. In: International Conference on Automated Planning and Scheduling (ICAPS), vol. 19 (2009)
Leurent, E.: An environment for autonomous driving decision-making (2018)
Linegang, M.P., et al.: Human-automation collaboration in dynamic mission planning: a challenge requiring an ecological approach. Proc. Human Fact. Ergon. Soc. Annual Meet. 50(23), 2482–2486 (2006)
Lucic, A., Haned, H., de Rijke, M.: Why does my model fail? contrastive local explanations for retail forecasting. In: Proceedings of the ACM Conference on Fairness, Accountability, and Transparency, pp. 90–98 (2020)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30 (2017)
Madumal, P., Miller, T., Sonenberg, L., Vetere, F.: Explainable reinforcement learning through a causal lens. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 2493–2500 (2020)
Mercado, J.E., Rupp, M.A., Chen, J.Y., Barnes, M.J., Barber, D., Procci, K.: Intelligent agent transparency in human-agent teaming for Multi-UxV management. Hum. Fact. 58(3), 401–415 (2016)
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
Mnih, V., et al.: Playing Atari with deep reinforcement learning (2013). https://arxiv.org/abs/1312.5602
Molnar, C.: Interpretable Machine Learning, 2 edn. (2022). https://christophm.github.io/interpretable-ml-book
Mothilal, R.K., Sharma, A., Tan, C.: Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the ACM Conference on Fairness, Accountability, and Transparency, pp. 607–617 (2020)
Nashed, S.B., Mahmud, S., Goldman, C.V., Zilberstein, S.: Causal explanations for sequential decision making under uncertainty (2022)
Nisioi, S., Štajner, S., Ponzetto, S.P., Dinu, L.P.: Exploring neural text simplification models. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp. 85–91 (2017)
Panigutti, C., Perotti, A., Pedreschi, D.: Doctor XAI: an ontology-based approach to black-box sequential data classification explanations. In: Proceedings of the ACM Conference on Fairness, Accountability, and Transparency, pp. 629–639 (2020)
Pouget, H., Chockler, H., Sun, Y., Kroening, D.: Ranking policy decisions (2020). arXiv preprint arXiv:2008.13607
Russell, J., Santos, E.: Explaining reward functions in Markov decision processes. In: Thirty-Second International FLAIRS Conference (2019)
Scharrer, L., Bromme, R., Britt, M.A., Stadtler, M.: The seduction of easiness: how science depictions influence laypeople’s reliance on their own evaluation of scientific information. Learn. Inst. 22(3), 231–243 (2012)
Shapley, L.S., et al.: A value for n-person games (1953)
Srikanth, N., Li, J.J.: Elaborative simplification: content addition and explanation generation in text simplification (2020). arXiv preprint arXiv:2010.10035
Stubbs, K., Hinds, P.J., Wettergreen, D.: Autonomy and common ground in human-robot interaction: a field study. IEEE Intell. Syst. 22(2), 42–50 (2007)
Sukkerd, R., Simmons, R., Garlan, D.: Tradeoff-focused contrastive explanation for mdp planning. In: 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp. 1041–1048. IEEE (2020)
Štrumbelj, E., Kononenko, I.: Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41, 647–665 (2014)
Wang, N., Pynadath, D.V., Hill, S.G.: The impact of POMDP-generated explanations on trust and performance in human-robot teams. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 997–1005 (2016)
Zhang, Y., Liao, Q.V., Bellamy, R.K.: Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making. In: Proceedings of the ACM Conference on Fairness, Accountability, and Transparency, pp. 295–305 (2020)
Acknowledgments
This work was supported in part by the National Science Foundation grant number IIS-1954782.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mahmud, S., Nashed, S.B., Goldman, C.V., Zilberstein, S. (2023). Estimating Causal Responsibility for Explaining Autonomous Behavior. In: Calvaresi, D., et al. Explainable and Transparent AI and Multi-Agent Systems. EXTRAAMAS 2023. Lecture Notes in Computer Science(), vol 14127. Springer, Cham. https://doi.org/10.1007/978-3-031-40878-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-40878-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40877-9
Online ISBN: 978-3-031-40878-6
eBook Packages: Computer ScienceComputer Science (R0)