让强化学习自己解释决策，提升移动网络资源分配的透明度与性能。
Self-Explaining Reinforcement Learning for Mobile Network Resource Allocation
- 用自解释神经网络替代传统策略网络，实现决策过程的局部可解释性。
- 在资源分配任务中性能接近顶尖深度学习方法，显著优于现有部署启发式算法。
- 生成的全局解释与已有解释方法高度一致，适合高风险场景应用。
深度强化学习虽强大，但缺乏透明性，限制了其在关键领域的应用。本文将自解释神经网络（SENN）引入强化学习，通过用SENN参数化PPO智能体的策略，生成内在的局部解释，并提出一种聚合方法得到全局解释。我们在移动网络资源分配问题上评估该方法，结果表明：性能仅比当前最优深度学习方法略低，但显著优于最佳部署的启发式算法；同时提取的全局解释与DeepLift和InputXGradient方法高度相关，证明SENN是高风险强化学习中的有前途候选方案。
原文摘要 · Abstract (English)
Deep reinforcement learning (DRL) methods, though powerful, often lack transparency, which limits their adoption in critical domains. We apply Self-Explaining Neural Networks (SENNs) to RL by parametrizing the policy of a PPO agent with a SENN, producing intrinsic local explanations, and propose a method for aggregating them into global explanations. We evaluate our approach on a mobile network resource allocation problem, our approach performs within a small margin of the state-of-the-art deep learning method and significantly outperforms the best deployed heuristic, while the extracted global explanations correlate strongly with DeepLift and InputXGradient, making SENNs a promising candidate for high-stakes RL.
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。