# Clustered Policy Decision Ranking

arXiv: https://arxiv.org/abs/2311.12970 · HTML: https://mlsanity.com/paper/2311.12970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 21 Nov 2023.

## Builds on (most cited first, 2 of 2)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Ranking Policy Decisions](https://mlsanity.com/paper/2008.13607/) (2020)

## Abstract (arXiv)

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.