#### Filter Results:

- Full text PDF available (38)

#### Publication Year

1986

2018

- This year (1)
- Last 5 years (14)
- Last 10 years (33)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Peter Auer, Thomas Jaksch, Ronald Ortner
- NIPS
- 2008

For undiscounted reinforcement learning in Markov decision processes (MDPs) we consider the total regret of a learning algorithm with respect to an optimal policy. In order to describe the transitionâ€¦ (More)

- Peter Auer, Ronald Ortner
- Periodica Mathematica Hungarica
- 2010

ABSTRACT. In the stochastic multi-armed bandit problem we consider a modification of the UCB algorithm of Auer et al. [4]. For this modified algorithm we give an improved bound on the regret withâ€¦ (More)

- Gabriele Pfurtscheller, Teodoro Solis-Escalante, Ronald Ortner, Patricia Linortner, G. R. Muller-Putz
- IEEE Transactions on Neural Systems andâ€¦
- 2010

This work introduces a hybrid brain-computer interface (BCI) composed of an imagery-based brain switch and a steady-state visual evoked potential (SSVEP)-based BCI. The brain switch (event relatedâ€¦ (More)

- Peter Auer, Ronald Ortner
- NIPS
- 2006

We present a learning algorithm for undiscounted reinforcement learning. Our interest lies in bounds for the algorithmâ€™s online performance after some finite number of steps. In the spirit of similarâ€¦ (More)

- Peter Auer, Ronald Ortner
- ECML
- 2004

- Peter Auer, Ronald Ortner, Csaba SzepesvÃ¡ri
- COLT
- 2007

Considering one-dimensional continuum-armed bandit problems, we propose an improvement of an algorithm of Kleinberg and a new set of conditions which give rise to improved rates. In particular, weâ€¦ (More)

- Ronald Ortner, Daniil Ryabko
- NIPS
- 2012

We derive sublinear regret bounds for undiscounted reinforcement learning in continuous state space. The proposed algorithm combines state aggregation with the use of upper confidence bounds forâ€¦ (More)

- Ronald Ortner
- ALT
- 2008

We consider an upper confidence bound algorithm for Markov decision processes (MDPs) with deterministic transitions. For this algorithm we derive upper bounds on the online regret (with respect to anâ€¦ (More)

- Ronald Ortner, B. Z. Allison, Gerd Korisek, H Gaggl, Gabriele Pfurtscheller
- IEEE Transactions on Neural Systems andâ€¦
- 2011

Brain-computer interface (BCI) systems allow people to send messages or commands without moving, and hence can provide an alternative communication and control channel for people with limited motorâ€¦ (More)

- Ronald Ortner, Daniil Ryabko, Peter Auer, RÃ©mi Munos
- ALT
- 2012

We consider the restless Markov bandit problem, in which the state of each arm evolves according to a Markov process independently of the learnerâ€™s actions. We suggest an algorithm that after T stepsâ€¦ (More)