发现并归因智能体的重复行为模式，让决策解释更精细可信。
Behaviour Discovery and Attribution for Explainable Reinforcement Learning
- 从状态-动作序列中聚类出连贯的行为簇，实现行为级解释。
- 在4个离线强化学习环境中验证，行为识别精度优于轨迹级基线。
- 适合需要可解释决策的高风险场景，如机器人、医疗与金融。
构建强化学习智能体的信任需理解其决策原因，尤其在机器人、医疗与金融等高风险应用中。现有可解释方法多聚焦单个状态或整段轨迹，仅提供局部步骤洞察或粗粒度的全程总结，忽略跨多个决策反复出现的策略与时间上延展的行为模式。本文提出一种完全离线、无需奖励信号的行为发现与分割框架，能将动作归因于有意义且可解释的行为片段，捕捉多轨迹中重复出现的模式。该方法从状态-动作序列中识别出一致的行为簇，并将个体动作归属到这些簇中，实现细粒度、以行为为中心的解释。在四个多样化的离线强化学习环境中的评估表明，该方法能发现有意义的行为模式，在保真度、人类偏好与簇内一致性方面均优于轨迹级基线。代码已公开。
原文摘要 · Abstract (English)
Building trust in reinforcement learning (RL) agents requires understanding why they make certain decisions, especially in high-stakes applications like robotics, healthcare, and finance. Existing explainability methods often focus on single states or entire trajectories, either providing only local, step-wise insights or attributing decisions to coarse, episodelevel summaries. Both approaches miss the recurring strategies and temporally extended patterns that actually drive agent behavior across multiple decisions. We address this gap by proposing a fully offline, reward-free framework for behavior discovery and segmentation, enabling the attribution of actions to meaningful and interpretable behavior segments that capture recurring patterns appearing across multiple trajectories. Our method identifies coherent behavior clusters from state-action sequences and attributes individual actions to these clusters for fine-grained, behavior-centric explanations. Evaluations on four diverse offline RL environments show that our approach discovers meaningful behaviors and outperforms trajectory-level baselines in fidelity, human preference, and cluster coherence. Our code is publicly available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。