EPrints submitted by Thomas Jaksch
Click here to see user's record. Number of EPrints submitted by this user: 5
Near-optimal Regret Bounds for Reinforcement Learning
Peter Auer, Thomas Jaksch and Ronald Ortner
(2007)
Working Paper, University of Leoben.
Near-optimal Regret Bounds for Reinforcement Learning
Peter Auer, Thomas Jaksch and Ronald Ortner
In:
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 21
Advances in Neural Information Processing Systems
, 21
.
(2009)
NIPS Foundation
, .
Near-optimal Regret Bounds for Reinforcement Learning
Peter Auer, Thomas Jaksch and Ronald Ortner
(2009)
Technical Report.
Chair for Informationtechnology, Leoben, Austria.
Near-optimal Regret Bounds for Reinforcement Learning
Peter Auer, Thomas Jaksch and Ronald Ortner
In: Nips 2008, 8-13 Dec 2008, Vancouver, Canada.
Near-optimal Regret Bounds for Reinforcement Learning
Peter Auer, Thomas Jaksch and Ronald Ortner
In: Nips 2008, 8-13 Dec 2008, Vancouver, Canada.
| 