Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths
英文标题：Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths
arXiv:2607.15440v1 Announce Type: new Abstract: 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 execut
打开原文相关 2.4 · 机会 1
2.1 KB
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.15440v1 Announce Type: new Abstract: 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 execut
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×