Near-optimal Regret Bounds for Reinforcement Learning

Translated title of the contribution: Near-optimal Regret Bounds for Reinforcement Learning

Thomas Jaksch, Ronald Ortner, Peter Auer

Research output: Contribution to journalArticleResearchpeer-review

282 Citations (Scopus)
Translated title of the contributionNear-optimal Regret Bounds for Reinforcement Learning
Original languageGerman
Pages (from-to)1563-1600
JournalJournal of machine learning research (JMLR)
Volume11
Publication statusPublished - 2010

Cite this