Extreme State Aggregation beyond MDPs
-
Altmetric Citations
Description
We consider a Reinforcement Learning setup without any (esp. MDP) assumptions on the environment. State aggregation and more generally feature reinforcement learning is concerned with mapping histories/raw-states to reduced/aggregated states. The idea behind both is that the resulting reduced process (approximately) forms a small stationary finite-state MDP, which can then be efficiently solved or learnt. We considerably generalize existing aggregation results by showing that even if the...[Show more]
Collections | ANU Research Publications |
---|---|
Date published: | 2014-10 |
Type: | Conference paper |
URI: | http://hdl.handle.net/1885/14699 |
Book Title: | Algorithmic Learning Theory: 25th International Conference, ALT 2014, Bled, Slovenia, October 8-10, 2014. Proceedings |
DOI: | 10.1007/978-3-319-11662-4_14 |
Access Rights: | Open Access |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
Hutter Extreme State Aggregation 2014.pdf | 204.89 kB | Adobe PDF |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator