强化学习中Shapley解释的近似方法
Approximating Shapley Explanations in Reinforcement Learning
AI总结：
本文提出FastSVERL方法，通过近似Shapley值实现强化学习解释的可扩展计算，以应对时间依赖、离线数据和智能体行为演化等挑战。
摘要：
强化学习在复杂决策环境中取得了显著成功，但其缺乏透明性限制了它在实践中的部署，尤其是在安全关键场景中。来自合作博弈论的Shapley值为解释强化学习提供了一个有原则的框架；然而，Shapley解释的计算成本是其应用的一个障碍。我们提出了FastSVERL，这是一种通过近似Shapley值来解释强化学习的可扩展方法。FastSVERL旨在应对强化学习的独特挑战，包括多步轨迹上的时间依赖性、从离线策略数据中学习，以及实时适应不断演化的智能体行为。FastSVERL为强化学习中有原则且严格的可解释性引入了一种实用且可扩展的方法。
英文摘要：
Reinforcement learning has achieved remarkable success in complex decision-making environments, yet its lack of transparency limits its deployment in practice, especially in safety-critical settings. Shapley values from cooperative game theory provide a principled framework for explaining reinforcement learning; however, the computational cost of Shapley explanations is an obstacle to their use. We introduce FastSVERL, a scalable method for explaining reinforcement learning by approximating Shapley values. FastSVERL is designed to handle the unique challenges of reinforcement learning, including temporal dependencies across multi-step trajectories, learning from off-policy data, and adapting to evolving agent behaviours in real time. FastSVERL introduces a practical, scalable approach for principled and rigorous interpretability in reinforcement learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
