398 citations
8 papers · 1 filter
Temporal Difference Updating without a Learning Rate
Marcus Hutter, Shane Legg
We derive an equation for temporal difference learning from statistical principles. Specifically, we start with the variational principle and then bootstrap to produce an updating…
Algorithmic Complexity Bounds on Future Prediction Errors
A. Chernov, M. Hutter, J. Schmidhuber
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor from the true d…
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…