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

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.