114 citations
6 papers · 1 filter
Universal Learning of Repeated Matrix Games
Jan Poland, Marcus Hutter
We study and compare the learning dynamics of two universal learning algorithms, one based on Bayesian learning and the other on prediction with expert advice. Both approaches have…
Master Algorithms for Active Experts Problems based on Increasing Loss Values
Jan Poland, Marcus Hutter
We specify an experts algorithm with the following characteristics: (a) it uses only feedback from the actions actually chosen (bandit setup), (b) it can be applied with countably…
Prediction with Expert Advice by Following the Perturbed Leader for General Weights
Marcus Hutter, Jan Poland
When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the a…
Tournament versus Fitness Uniform Selection
Shane Legg, Marcus Hutter, Akshat Kumar
In evolutionary algorithms a critical parameter that must be tuned is that of selection pressure. If it is set too low then the rate of convergence towards the optimum is likely to…
Optimality of Universal Bayesian Sequence Prediction for General Loss and Alphabet
Marcus Hutter
Various optimality properties of universal sequence predictors based on Bayes-mixtures in general, and Solomonoff's prediction scheme in particular, will be studied. The probabilit…
Bayesian Treatment of Incomplete Discrete Data applied to Mutual Information and Feature Selection
Marcus Hutter, Marco Zaffalon
Given the joint chances of a pair of random variables one can compute quantities of interest, like the mutual information. The Bayesian treatment of unknown chances involves comput…