Learning Agents with Evolving Hypothesis Classes
Sunehag, Peter; Hutter, Marcus
Description
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
Collections | ANU Research Publications |
---|---|
Date published: | 2013 |
Type: | Conference paper |
URI: | http://hdl.handle.net/1885/65759 |
Source: | Learning Agents with Evolving Hypothesis Classes |
DOI: | 10.1007/978-3-642-39521-5_16 |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Sunehag_Learning_Agents_with_Evolving_2013.pdf | 167.33 kB | Adobe PDF | Request a copy |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 20 July 2017/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator