Clustered Policy Decision Ranking
Confirmation: I accept the constraint that If the paper will be accepted at least one of the authors will attend the workshop and present the work
Keywords: reinforcement learning, causality, policy simplification, clustering
TL;DR: 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.
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.
Submission Type: Short Paper
Submission Number: 2
Loading