398 citations · 1.8k across the 163 of their papers we have counts for
4 papers · 2 filters
Distribution of Mutual Information
Marcus Hutter
The mutual information of two random variables i and j with joint probabilities t_ij is commonly used in learning Bayesian nets as well as in many other fields. The chances t_ij ar…
Market-Based Reinforcement Learning in Partially Observable Worlds
Ivo Kwee, Marcus Hutter, Juergen Schmidhuber
Unlike traditional reinforcement learning (RL), market-based RL is in principle applicable to worlds described by partially observable Markov Decision Processes (POMDPs), where an…
Fitness Uniform Selection to Preserve Genetic Diversity
Marcus Hutter
In evolutionary algorithms, the fitness of a population increases with time by mutating and recombining individuals and by a biased selection of more fit individuals. The right sel…
General Loss Bounds for Universal Sequence Prediction
Marcus Hutter
The Bayesian framework is ideally suited for induction problems. The probability of observing at time , given past observations can be computed with Bayes'…