Developpement autonome des comportements de base dun agent
Date
2005
Authors
Buffet, Olivier
Dutech, Alain
Charpillet, Francois
Journal Title
Journal ISSN
Volume Title
Publisher
Hermes Science Publications
Abstract
The problem addressed in this article is that of automatically designing autonomous agents having to solve complex tasks involving several -and possibly concurrent- objectives. We propose a modular approach based on the principles of action selection where the actions recommanded by several basic behaviors are combined in a global decision. In this framework, our main contribution is a method making an agent able to automatically define and build the basic behaviors it needs through incremental reinforcement learning methods. This way, we obtain a very autonomous architecture requiring very few hand-coding. This approach is tested and discussed on a representative problem taken from the "tile-world".
Description
Keywords
Keywords: Decision theory; Learning systems; Markov processes; Markov Decision Problems; Multiple Motivations; Reinforcement Learning; Autonomous agents Markov Decision Problems; Multiple Motivations; Reinforcement Learning
Citation
Collections
Source
Revue d'Intelligence Artificielle
Type
Journal article