# Peter Auer

**Peter Auer**,

an Austrian mathematician and computer scientist, full professor and chair for information technology at University of Leoben, also associated with the Institute for Theoretical Computer Science, Graz University of Technology ^{[2]} . He holds a Ph.D. in technical mathematics in 1992 from Vienna University of Technology, and a Habilitation in 1997 from Graz University of Technology on the topic of information processing and probability theory ^{[3]} . His research interests include on machine learning, neural networks, symbolic computation, and computational complexity theory.

## Contents

# Bandit Problems

In probability theory, the multi-armed bandit problem faces the tradeoff between exploitation of the slot machine that has the highest expected payoff and exploration to get more information about the expected payoffs of the other machines. The trade-off between exploration and exploitation is also topic in reinforcement learning ^{[4]}. The gambler has to decide at time steps t = 1, 2, ... which of the finitely many available arms to pull. Each arm produces a reward in a stochastic manner. The goal is to maximize the reward accumulated over time. In 2002, along with Nicolò Cesa-Bianchi and Paul Fischer, Peter Auer introduced the **UCB1** (Upper Confidence Bounds) bandit algorithm ^{[5]}, which was applied as selection algorithm UCT to Monte-Carlo Tree Search as elaborated by Levente Kocsis and Csaba Szepesvári in 2006 ^{[6]}.

# Selected Publications

^{[7]} ^{[8]}

## 1990 ...

- Peter Auer (
**1991**).*Solving String Equations with Constant Restrictions*. IWWERT 1991 - Peter Auer (
**1991**).*Unification in the Combination of Disjoint Theories*. IWWERT 1991 - Peter Auer (
**1993**).*On-line learning of rectangles in noisy environments*. COLT 1993, ACM Press - Peter Auer, Nicolò Cesa-Bianchi (
**1994**).*On-line learning with malicious noise and the closure algorithm*. Algorithmic Learning Theory, LNAI, Springer - Peter Auer, Robert Holte, Wolfgang Maass (
**1995**).*Theory and Applications of Agnostic PAC-Learning with Small Decision Trees*. ICML 1995 - Peter Auer (
**1997**).*Learning Nested Differences in the Presence of Malicious Noise*. Theoretical Computer Science, Vol. 185, No. 1 - Peter Auer, Manfred K. Warmuth (
**1998**).*Tracking the best Disjunction*. Machine Learning, Vol. 32, pdf - Peter Auer, Nicolò Cesa-Bianchi, Yoav Freund, Robert Schapire (
**1998**).*Gambling in a rigged casino: The adversarial multi-arm bandit problem*. NeuroCOLT2, pdf

## 2000 ...

- Peter Auer, Stephen Kwek, Wolfgang Maass, Manfred K. Warmuth (
**2000**).*Learning of Depth Two Neural Networks with Constant Fan-in at the Hidden Nodes*. Electronic Colloquium on Computational Complexity, Vol. 7 - Peter Auer (
**2000**).*Using Upper Confidence Bounds for Online Learning*. FOCS 2000 - Peter Auer, Nicolò Cesa-Bianchi, Yoav Freund, Robert Schapire (
**2002**).*The Nonstochastic Multiarmed Bandit Problem*. SIAM Journal on Computing, Vol. 32, No. 1, 2001 pdf - Peter Auer, Nicolò Cesa-Bianchi, Paul Fischer (
**2002**).*Finite-time Analysis of the Multiarmed Bandit Problem*. Machine Learning, Vol. 47, No. 2, pdf - Peter Auer (
**2002**).*Using Confidence Bounds for Exploitation-Exploration Trade-offs*. Journal of Machine Learning Research, Vol. 3, Special Issue on Computational Learning Theory, pdf - Peter Auer, Ronald Ortner (
**2006**).*Logarithmic online regret bounds for undiscounted reinforcement learning*. NIPS 2006, pdf - Peter Auer (
**2008**).*Learning with Malicious Noise*. Encyclopedia of Algorithms

## 2010 ...

- Peter Auer, Ronald Ortner (
**2010**).*UCB revisited: Improved regret bounds for the stochastic multi-armed bandit problem*. Periodica Mathematica Hungarica, Vol. 61, Nos. 1-2, 2011 pdf - Peter Auer (
**2011**).*Exploration and Exploitation in Online Learning*. ICAIS 2011 - Peter Auer (
**2011**).*UCRL and Autonomous Exploration*. EWRL 2011 - Peter Auer, Marcus Hutter, Laurent Orseau (
**2013**).*Reinforcement Learning*. Dagstuhl Reports, Vol. 3, No. 8, DOI: 10.4230/DagRep.3.8.1, URN: urn:nbn:de:0030-drops-43409 - Ronald Ortner, Daniil Ryabko, Peter Auer, Rémi Munos (
**2014**).*Regret bounds for restless Markov bandits*. Theoretical Computer Science 558, pdf

# External Links

- Homepage Peter Auer
- CiT - Chair of Information Technology at the MUL
- The Mathematics Genealogy Project - Peter Auer
- Peter Auer: Informationstechnologie, Montanuniversität Leoben | 21.02.2003 | APA-OTS (German)

# References

- ↑ Homepage Peter Auer
- ↑ Homepage Peter Auer
- ↑ Peter Auer: Informationstechnologie, Montanuniversität Leoben | 21.02.2003 | APA-OTS (German)
- ↑ Multi-armed bandit from Wikipedia
- ↑ Peter Auer, Nicolò Cesa-Bianchi, Paul Fischer (
**2002**).*Finite-time Analysis of the Multiarmed Bandit Problem*. Machine Learning, Vol. 47, No. 2, pdf - ↑ Levente Kocsis, Csaba Szepesvári (
**2006**).*Bandit based Monte-Carlo Planning*ECML-06, LNCS/LNAI 4212, pdf - ↑ Publikationen von Prof. Dr. Peter Auer
- ↑ dblp: Peter Auer