Self-Growth of Basic Behaviors in an Action Selection Based Agent

Olivier Buffet (1, 2) , Alain Dutech (1) , François Charpillet (1)

1 MAIA - Autonomous intelligent machine
2 SML - Statistical Machine Learning Group

We investigate on designing agents facing multiple objectives simultaneously, that creates difficult situations, even if each objective is of low complexity. The present paper builds on an existing action selection process based on basic behaviors (resulting in a modular architecture) and proposes an algorithm for automatically selecting and learning the required basic behaviors through an incremental Reinforcement Learning approach. This leads to a very autonomous architecture, as the hand-coding is here reduced to its minimum.

Mots clés: Markov Decision Problems; Reinforcement Learning; Multiple Motivations

Domaines: Intelligence artificielle [cs.AI]

Olivier Buffet, Alain Dutech, François Charpillet. Self-Growth of Basic Behaviors in an Action Selection Based Agent. Eighth International Conference on Simulation of Adaptive Behavior (SAB'04), Jul 2004, Los Angeles, CA, USA, pp.223-232. ⟨inria-00000573⟩