Online Regret Bounds for Undiscounted Continuous Reinforcement Learning

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

Authors

Details

Translated title of the contributionOnline Regret Bounds for Undiscounted Continuous Reinforcement Learning
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 25
PublisherMIT Press
Pages1772-1780
Publication statusPublished - 2012