Explanation-Aware Experience Replay in Rule-Dense Environments
This addresses the challenge of integrating RL agents into complex, rule-regulated environments, offering a method to enhance learning efficiency without extensive reward tuning.
The paper tackled the problem of improving Reinforcement Learning (RL) performance in rule-dense environments like autonomous driving by proposing Explanation-Aware Experience Replay (XAER), which organizes experiences based on explanations to sample them more effectively. The result showed that XA versions of algorithms like DQN, TD3, and SAC consistently outperformed traditional baselines, indicating that explanation engineering can replace reward engineering in such settings.
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.