Universal knowledge-seeking agents for stochastic environments
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 arbitrary countable classes and priors, we focus on the especially interesting case where all stochastic computable environments are considered and the prior is based on Solomonoff’s universal prior. Among other properties, we show that KL-KSA learns...[Show more]
|Collections||ANU Research Publications|
|Orseau et al Universal Knowledge Seeking Agents 2013.pdf||411.33 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.