Handling Model Uncertainty and Multiplicity in Explanations via Model Reconciliation

By Sarath Sreedharan, Tathagata Chakraborti, Subbarao Kambhampati. 2018

71 citations recorded by the source corpus.

Model reconciliation has been proposed as a way for an agent to explain its decisions to a human who may have a different understanding of the same planning problem by explaining its decisions in terms of these model differences.However, often the human's mental model (and hence the difference) is not known precisely and such explanations cannot be readily computed.In this paper, we show how the explanation generation process evolves in the presence of such model uncertainty or incompleteness by generating {\em conformant explanations} that are applicable to a set of possible models.We also show how such explanations can contain superfluous informationand how such redundancies can be reduced using conditional explanations to iterate with the human to attain common ground. Finally, we will introduce an anytime version of this approach and empirically demonstrate the trade-offs involved in the different forms of explanations in terms of the computational overhead for the agent and the communication overhead for the human.We illustrate these concepts in three well-known planning domains as well as in a demonstration on a robot involved in a typical search and reconnaissance scenario with an external human supervisor.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety, Robustness & Interpretability

Citations in the corpus

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “ural language processing, health records analysis, recidivism prediction, model explanations for planning and robotics, and so on [74, 201, 280].”
Model Recognition as Planning (2019, methodology): “…to conform two PDDL models, where one of them can be an annotated model or an empty model, with respect to a fully observed optimal plan computed with one of the two models (Chakraborti et al. 2017; Sreedharan, Chakraborti, and Kambhampati 2018; Chakraborti, Sreedharan, and Kambhampati 2018).”