Alain Dutech  Home/Search
Context
Related
| loria.fr/~dutech/Papers/eis98.ps.gz Cached: PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
PS.gz PS Image Update HelpFrom: loria.fr/~dutech/papers (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: This paper presents a computational model for the delicate problem of action-selection in an autonomous system. Unlike other approaches, our model is not specified beforehand but learns by itself how to improve its performances. The main idea behind our work is for the controller to develop the needed hierarchy of actions for the system to achieve its tasks. Drawing on ideas presented by Aitken, we propose some augmentations to use the correlated activities of the system and some... (Update)
Similar documents based on text: More All
0.3: Learning to Weigh Basic Behaviors in Scalable Agents - Buffet, Dutech, Charpillet (Correct)
0.2: A Self-Made Agent Based on Action-Selection - Buffet, Dutech (2003) (Correct)
0.2: Looking for Scalable Agents - Buffet, Dutech (Correct)
BibTeX entry: (Update)
@misc{ dutech-selforganizing,
author = "Alain Dutech",
title = "Self-Organizing Autonomous Robot Controller.",
url = "citeseer.ist.psu.edu/401376.html" }
Citations (may not include all citations):1053 Genetic programming: on the programming of computers by mean.. (context) - KOZA - 1992
60 Learning to perceive and act by trial and errors (context) - WHITEHEAD, BALLARD - 1991
19 real learning problems (context) - et, Real - 1993
4 Automatic generation of adaptive programs - et, STOFFEL - 1996
1 Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (context) - SCHMIDHUBER, ZHAO et al. - 1996
1 Report of the Artificial Intelligence Lab (context) - BROOKS, layered et al. - 1985
Documents on the same site (http://www.loria.fr/~dutech/papers.html): More
Solving POMDPs using selected past events. - Dutech (2000) (Correct)
Multi-Agent Systems by Incremental Gradient Reinforcement .. - Dutech, Buffet.. (2001) (Correct)
Incremental Reinforcement Learning for designing.. - Buffet, Dutech.. (2001) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC