A Unified Algorithm for Stochastic Path ProblemsDownload PDFOpen Website

Christoph Dann, Chen-Yu Wei, Julian Zimmert

2023 (modified: 24 Apr 2023)ALT 2023Readers: Everyone
Abstract: We study reinforcement learning in stochastic path (SP) problems. The goal in these problems is to maximize the expected sum of rewards until the agent reaches a terminal state. We provide the firs...
0 Replies