Actor-Critic models of animal control -- a critique of reinforcement learning (2004)
by
Florentin Wörgötter
| Venue: | PROCEEDING OF FOURTH INTERNATIONAL ICSC SYMPOSIUM ON ENGINEERING OF INTELLIGENT SYSTEMS |
| Citations: | 2 - 0 self |
BibTeX
@INPROCEEDINGS{Wörgötter04actor-criticmodels,
author = {Florentin Wörgötter},
title = {Actor-Critic models of animal control -- a critique of reinforcement learning},
booktitle = {PROCEEDING OF FOURTH INTERNATIONAL ICSC SYMPOSIUM ON ENGINEERING OF INTELLIGENT SYSTEMS},
year = {2004},
publisher = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In this article we will compare traditional reinforcement learning techniques with a novel correlation based algorithm. We will discuss several problems which occur in reward-based reinforcement learning and outline alternative solutions. An example of a robot control task shown at the end will support our claims.
