Universal Knowledge-Seeking Agents for Stochastic Environments
Date
Authors
Orseau, Laurent
Lattimore, Tor
Hutter, Marcus
Journal Title
Journal ISSN
Volume Title
Publisher
Landes Bioscience/Springer Science+Business Media
Abstract
We define an optimal Bayesian knowledge-seeking agent, KL-KSA, designed for countable hypothesis classes of stochastic environments and whose goal is to gather as much information about the unknown world as possible. Although this agent works for arbitrar
Description
Keywords
Citation
Collections
Source
Lecture Notes in Artificial Intelligence
Type
Book Title
Entity type
Access Statement
Open Access