Causal Explanations for Sequential Decision Making Under Uncertainty
This provides a flexible causal explanation method for AI agents in uncertain environments, though it appears incremental as it builds on existing causal reasoning paradigms.
The paper tackles the problem of explaining stochastic, sequential decision-making by introducing a novel framework based on structural causal models, which can identify multiple distinct explanations for agent actions, with results including exact methods, approximations, and runtime bounds.
We introduce a novel framework for causal explanations of stochastic, sequential decision-making systems built on the well-studied structural causal model paradigm for causal reasoning. This single framework can identify multiple, semantically distinct explanations for agent actions -- something not previously possible. In this paper, we establish exact methods and several approximation techniques for causal inference on Markov decision processes using this framework, followed by results on the applicability of the exact methods and some run time bounds. We discuss several scenarios that illustrate the framework's flexibility and the results of experiments with human subjects that confirm the benefits of this approach.