Sciweavers

CORR
2002
Springer

Self-Optimizing and Pareto-Optimal Policies in General Environments based on Bayes-Mixtures

13 years 3 months ago
Self-Optimizing and Pareto-Optimal Policies in General Environments based on Bayes-Mixtures
The problem of making sequential decisions in unknown probabilistic environments is studied. In cycle t action yt results in perception xt and reward rt, where all quantities in general may depend on the complete history. The perception xt and reward rt are sampled from the (reactive) environmental probability distribution
Marcus Hutter
Added 18 Dec 2010
Updated 18 Dec 2010
Type Journal
Year 2002
Where CORR
Authors Marcus Hutter
Comments (0)