Explanation-Aware Experience Replay in Rule-Dense Environments
arXiv:2109.14711 · doi:10.1109/LRA.2021.3135927
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.
arXiv commentTo appear in IEEE Robotics and Automation Letters (IEEE RA-L). Please cite the published version
References in corpus (9)
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Prioritized Experience Replay
- Model-Based Reinforcement Learning for Atari
- A Lyapunov-based Approach to Safe Reinforcement Learning
- From Philosophy to Interfaces: an Explanatory Method and a Tool Inspired by Achinstein's Theory of Explanation
- Experience Replay Optimization
- Combining Experience Replay with Exploration by Random Network Distillation
- Agree to Disagree: Subjective Fairness in Privacy-Restricted Decentralised Conflict Resolution
- Revisiting Prioritized Experience Replay: A Value Perspective