Year: 2023
Type: preprint
Abstract: Policies trained via reinforcement learning (RL) are often very complex even for simple tasks. In an episode with n time steps, a policy will make n decisions on actions to take, many of which may appear non-intuitive to the observer. Moreover, it is not clear which of these decisions directly contribute towards achieving the reward and how significant their contribution is. Given a trained policy, we propose a black-box method based on statistical covariance estimation that clusters the states of the environment and ranks each cluster according to the importance of decisions made in its states. We compare our measure against a previous statistical fault localization based ranking procedure.
Source: arXiv (Cornell University)
Authors: Levin, Mark, Chockler, Hana
Institutions: University of Maryland, College Park, King's College London
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4388964495