Ranking Policy Decisions

TL;DR

This paper introduces a statistical fault localisation method to rank environment states by decision importance in RL policies, enabling the creation of simpler, interpretable policies without significant performance loss.

Contribution

The paper presents a novel black-box ranking method for policy decisions in RL, facilitating interpretability and policy simplification through decision pruning.

Findings

Pruned policies perform comparably to original policies.

Naive ranking methods like state visitation frequency are ineffective.

The proposed method aids in understanding and explaining RL policies.

Abstract

Policies trained via Reinforcement Learning (RL) are often needlessly complex, making them difficult to analyse and interpret. In a run with $n$ time steps, a policy will make $n$ decisions on actions to take; we conjecture that only a small subset of these decisions delivers value over selecting a simple default action. Given a trained policy, we propose a novel black-box method based on statistical fault localisation that ranks the states of the environment according to the importance of decisions made in those states. We argue that among other things, the ranked list of states can help explain and understand the policy. As the ranking method is statistical, a direct evaluation of its quality is hard. As a proxy for quality, we use the ranking to create new, simpler policies from the original ones by pruning decisions identified as unimportant (that is, replacing them by default actions) and measuring the impact on performance. Our experiments on a diverse set of standard benchmarks demonstrate that pruned policies can perform on a level comparable to the original policies. Conversely, we show that naive approaches for ranking policy decisions, e.g., ranking based on the frequency of visiting a state, do not result in high-performing pruned policies.