Peter Auer

From Chessprogramming wiki
Revision as of 10:25, 1 May 2020 by GerdIsenberg (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Home * People * Peter Auer

Peter Auer [1]

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.

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 ...

2000 ...

2010 ...

External Links

References

Up one Level