Développement autonome des comportements de base d'un agent
Revue d'Intelligence Artificielle (RIA)
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 .