结合决策树剪枝的可解释强化学习
Interpretable reinforcement learning with decision-tree pruning
- Ludwig-Maximilians-University Munich（慕尼黑大学）
- Siemens AG（西门子公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出一种结合决策树剪枝的可解释强化学习方法，通过定义结构感知与使用感知算子简化策略，在经典控制及MuJoCo基准上验证其可保持高性能并提升可解释性。
AI中文摘要：
强化学习策略难以检查，而对其进行解释是实现可信赖性的前提。将训练好的策略转换为显式决策树规则可提升透明度，但生成的规则产物往往过于复杂，超出人类理解能力。我们提出一种剪枝流程，该流程在保留任务性能的同时简化此类基于规则的策略，并使对策略的编辑可审计。此流程定义了一小组结构感知和使用感知的算子，通过重新执行策略来评估候选编辑，以衡量回报和可解释性代理指标，这揭示了从复杂策略结构到紧凑策略结构的转换过程。我们在经典控制任务和MuJoCo基准上研究了该方法，剪枝轨迹显示其在保持高性能的同时，实现了一致的可解释性提升。
英文摘要：
Reinforcement learning policies are difficult to inspect, but interpreting them is a prerequisite for trustworthiness. Converting a trained policy into explicit decision-tree rules improves transparency and the resulting artifacts often remain too complex for human understanding. We present a pruning process that simplifies such rule-based policies while preserving task performance and making edits to the policy auditable. The process defines a small set of structural and usage-aware operators and evaluates candidate edits by re-executing the policy to measure return and interpretability proxies. This exposes an transformation process from complex to compact policy structures. We investigate this approach on classic control and MuJoCo benchmarks, where pruning traces reveal consistent interpretability improvements while maintaining high performance.
