Explanation-Aware Experience Replay in Rule-Dense Environments

TL;DR

This paper introduces Explanation-Aware Experience Replay (XAER), a method that organizes experience buffers based on rule-based explanations to improve reinforcement learning in rule-dense environments like autonomous driving.

Contribution

It proposes a novel experience replay technique that leverages explainable rules to enhance learning efficiency and performance in complex, rule-rich environments.

Findings

XAER outperforms traditional prioritized experience replay methods.

Explanation engineering can substitute reward engineering in environments with explainable features.

The method is validated across multiple navigation environments and learning tasks.

Abstract

Human environments are often regulated by explicit and complex rulesets. Integrating Reinforcement Learning (RL) agents into such environments motivates the development of learning mechanisms that perform well in rule-dense and exception-ridden environments such as autonomous driving on regulated roads. In this paper, we propose a method for organising experience by means of partitioning the experience buffer into clusters labelled on a per-explanation basis. We present discrete and continuous navigation environments compatible with modular rulesets and 9 learning tasks. For environments with explainable rulesets, we convert rule-based explanations into case-based explanations by allocating state-transitions into clusters labelled with explanations. This allows us to sample experiences in a curricular and task-oriented manner, focusing on the rarity, importance, and meaning of events. We label this concept Explanation-Awareness (XA). We perform XA experience replay (XAER) with intra and inter-cluster prioritisation, and introduce XA-compatible versions of DQN, TD3, and SAC. Performance is consistently superior with XA versions of those algorithms, compared to traditional Prioritised Experience Replay baselines, indicating that explanation engineering can be used in lieu of reward engineering for environments with explainable features.