Logarithmic online regret bounds for undiscounted reinforcement learning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Details

Translated title of the contributionLogarithmic online regret bounds for undiscounted reinforcement learning
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 19
PublisherMIT Press
Pages49-56
Publication statusPublished - 2007