arXiv cs.LG
· Papers
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 execution resets it to the