Learning agents with evolving hypothesis classes
It has recently been shown that a Bayesian agent with a universal hypothesis class resolves most induction problems discussed in the philosophy of science. These ideal agents are, however, neither practical nor a good model for how real science works. We here introduce a framework for learning based on implicit beliefs over all possible hypotheses and limited sets of explicit theories sampled from an implicit distribution represented only by the process by which it generates new hypotheses. We...[Show more]
|Collections||ANU Research Publications|
|Sunehag and Hutter Learning Agents 2013.pdf||145.94 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.