Paul Fischer

From Chessprogramming wiki
Jump to: navigation, search

Home * People * Paul Fischer

Paul Fischer [1]

Paul Fischer,
a German mathematician, computer scientist and associate professor and head of the algorithms, logic, and graphs (AlgoLoG) section [2] at Technical University of Denmark, Kongens Lyngby. He holds a M.Sc. in 1983 and Ph.D. 1986 in mathematics from Bielefeld University, and a habilitation in CS from University of Dortmund in 1995 [3]. His research interests include computability theory such as reduction of recursively enumerable Turing degrees and weak truth-table degrees, algorithmic learning, bandit problems and time series analysis. He has also written about GUI programming using Java Swing [4].

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 [5]. 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 Peter Auer and Nicolò Cesa-Bianchi, Paul Fischer introduced the UCB1 (Upper Confidence Bounds) bandit algorithm [6], which was applied as selection algorithm UCT to Monte-Carlo Tree Search as elaborated by Levente Kocsis and Csaba Szepesvári in 2006 [7].

Selected Publications

[8] [9]

1983 ...

1990 ...

2000 ...

2010 ...

External Links


Up one Level