Clustered Policy Decision Ranking

arXiv:2311.12970v2 Announce Type: replace
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 …

abstract arxiv clear cs.ai cs.lg decision decisions policies policy ranking reinforcement reinforcement learning simple tasks the observer type via will