提出时空强化学习框架，解决非马尔可夫网络流量下的路由优化问题。
Spatial-Temporal Reinforcement Learning for Network Routing with Non-Markovian Traffic
- 融合时空特征建模，捕捉网络拓扑结构与历史状态依赖
- 训练阶段性能提升超19%，推理阶段提升7%
- 适合动态拓扑网络中的智能路由系统研究者
强化学习（RL）已被广泛用于通信网络中的数据包路由，但传统RL方法依赖马尔可夫假设，认为当前状态包含决策所需全部信息。实际上，互联网流量具有非马尔可夫特性，历史状态对路由性能仍有影响。此外，常见的深度强化学习方法使用神经网络等函数逼近器，未能建模网络拓扑的的空间结构。为此，我们构建了一个具有非马尔可夫流量的网络环境，并提出一种时空强化学习（STRL）框架用于数据包路由。该方法在训练阶段性能优于传统基线超过19%，推理阶段也提升7%，即使在网络拓扑发生变化时依然有效。
原文摘要 · Abstract (English)
Reinforcement Learning (RL) has been widely used for packet routing in communication networks, but traditional RL methods rely on the Markov assumption that the current state contains all necessary information for decision-making. In reality, internet traffic is non-Markovian, and past states do influence routing performance. Moreover, common deep RL approaches use function approximators, such as neural networks, that do not model the spatial structure in network topologies. To address these shortcomings, we design a network environment with non-Markovian traffic and introduce a spatial-temporal RL (STRL) framework for packet routing. Our approach outperforms traditional baselines by more than 19% during training and 7% for inference despite a change in network topology.
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。