Preprint
Jul 2026
Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths
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, complementary to the edge-level CCB bound and more informative on structured graphs with polynomially many source-to-goal paths.
Guni Sharon, Wei Zhang
· 0 citations