Model-Free Model Reconciliation

Designing agents capable of explaining complex sequential decisions remain a significant open problem in automated decision-making. Recently, there has been a lot of interest in developing approaches for generating such explanations for various decision-making paradigms. One such approach has been the idea of {\em explanation as model-reconciliation}. The framework hypothesizes that one of the common reasons for the user's confusion could be the mismatch between the user's model of the task and the one used by the system to generate the decisions. While this is a general framework, most works that have been explicitly built on this explanatory philosophy have focused on settings where the model of user's knowledge is available in a declarative form. Our goal in this paper is to adapt the model reconciliation approach to the cases where such user models are no longer explicitly provided. We present a simple and easy to learn labeling model that can help an explainer decide what information could help achieve model reconciliation between the user and the agent.

[1]  Miao‐kun Sun Trends in cognitive sciences , 2012 .

[2]  Subbarao Kambhampati,et al.  Balancing Explicability and Explanation in Human-Aware Planning , 2017, AAAI Fall Symposia.

[3]  Marvin A. Carlson Editor , 2015 .

[4]  David Abel,et al.  simple_rl: Reproducible Reinforcement Learning in Python , 2019, RML@ICLR.

[5]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[6]  Subbarao Kambhampati,et al.  Planning with Explanatory Actions: A Joint Approach to Plan Explicability and Explanations in Human-Aware Planning , 2019, ArXiv.

[7]  Bradley Hayes,et al.  Improving Robot Controller Transparency Through Autonomous Policy Explanation , 2017, 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI.

[8]  Susanne Biundo-Stephan,et al.  Making Hybrid Plans More Clear to Human Users - A Formal Approach for Generating Sound Explanations , 2012, ICAPS.

[9]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[10]  Yu Zhang,et al.  Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy , 2017, IJCAI.

[11]  Pascal Poupart,et al.  Minimal Sufficient Explanations for Factored Markov Decision Processes , 2009, ICAPS.

[12]  Subbarao Kambhampati,et al.  (When) Can AI Bots Lie? , 2019, AIES.

[13]  Maria Fox,et al.  Explainable Planning , 2017, ArXiv.

[14]  Tim Miller,et al.  Explanation in Artificial Intelligence: Insights from the Social Sciences , 2017, Artif. Intell..

[15]  Yu Zhang,et al.  Plan explicability and predictability for robot task planning , 2015, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Subbarao Kambhampati,et al.  Handling Model Uncertainty and Multiplicity in Explanations via Model Reconciliation , 2018, ICAPS.

[17]  Anca D. Dragan,et al.  Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior , 2018, NeurIPS.

[18]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[19]  Thomas G. Dietterich The MAXQ Method for Hierarchical Reinforcement Learning , 1998, ICML.

[20]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.