"Learning in Structured MDPs with Convex Cost Functions: Improved Regret ..."

Shipra Agrawal, Randy Jia (2022)

Details and statistics

DOI: 10.1287/OPRE.2022.2263

access: closed

type: Journal Article

metadata version: 2022-08-08

a service of  Schloss Dagstuhl - Leibniz Center for Informatics