Timezone: »
Poster
Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning
Peter Auer · Ronald Ortner
Author Information
Peter Auer (Montanuniversitaet Leoben)
Ronald Ortner (Montanuniversitaet Leoben)
More from the Same Authors
-
2014 Workshop: Autonomously Learning Robots »
Gerhard Neumann · Joelle Pineau · Peter Auer · Marc Toussaint -
2011 Poster: PAC-Bayesian Analysis of Contextual Bandits »
Yevgeny Seldin · Peter Auer · Francois Laviolette · John Shawe-Taylor · Ronald Ortner -
2008 Poster: Near-optimal Regret Bounds for Reinforcement Learning »
Peter Auer · Thomas Jaksch · Ronald Ortner -
2008 Spotlight: Near-optimal Regret Bounds for Reinforcement Learning »
Peter Auer · Thomas Jaksch · Ronald Ortner -
2006 Workshop: On-line Trading of Exploration and Exploitation »
Peter Auer