发表机构
Texas A&M University（德克萨斯A&M大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究随机重置路径寻找（SRP）问题，它在已知有向图上，边成功概率未知。提出 Log - Dijkstra 元算法及 PathUCB、PathTS 实例，给出 PathUCB 路径级遗憾界，实验表明 PathTS 性能佳但有对抗实例，推荐其为实用默认算法。
AI 中文摘要
我们引入随机重置路径寻找（SRP），这是一个在已知有向图上的 episodic 学习问题，其边的固定成功概率未知。在每个情节中，智能体选定一条从源到目标的路径，执行中边的失败会将其重置回源。SRP 涵盖量子中继网络中的纠缠分布、闪电网络中的支付路由等场景。我们表明全局重置结构使最优策略为开环，将 SRP 置于组合级联强盗（CCB）框架内。我们提出了带有 UCB（PathUCB）和汤普森采样（PathTS）实例的 Log - Dijkstra 元算法。主要技术成果是为 PathUCB 给出路径级遗憾界，通过每条路径的复杂度 C(π)分解次优路径上的遗憾。实验支持了理论，表明 PathTS 通常有最佳经验性能，但存在对抗实例使 PathTS 无法收敛。
英文摘要
We introduce Stochastic Reset Pathfinding (SRP), an episodic learning problem on a known directed graph with unknown stationary edge success probabilities. In each episode, the agent commits to a source-to-goal path, and any edge failure during execution resets it to the source. SRP captures settings such as entanglement distribution in quantum repeater networks, payment routing on the Lightning Network, and delivery in unreliable mesh networks. We show that the global-reset structure makes the optimal policy open-loop, placing SRP within the combinatorial cascading bandit (CCB) framework. We propose a Log-Dijkstra meta-algorithm with UCB (PathUCB) and Thompson Sampling (PathTS) instantiations. Our main technical result is a path-level regret bound for PathUCB that decomposes regret over suboptimal paths via a per-path complexity C(pi) combining each edge's prefix and suffix reliability. The bound is complementary to the edge-level CCB bound and more informative on structured graphs with polynomially many source-to-goal paths. Experiments on quantum-network, layered-DAG, grid-world, and Erdos-Renyi domains support the theory and show that PathTS typically achieves the best empirical performance among the algorithms tested. We then exhibit an adversarial instance on which PathTS fails to converge, consistent with a known exponential obstruction for combinatorial Thompson Sampling on multiplicative-reward problems. We recommend PathTS as the practical default while cautioning that adversarial instances exist.
