1#1

SOS++: Finding Smart Behaviors Using Learning and Evolution

Bertrand Mesot1, Eduardo Sanchez1, Carlos-Andres Peña1 and Andres Perez-Uribe2

1Swiss Federal Institute of Technology, EPFL-LSL, Lausanne (Switzerland)
2Swiss Federal Institute of Technology, EPFL-LSA, Lausanne (Switzerland)

Abstract:

We present SOS++,  a bioinspired method combining evolution  and learning,  allowing the automatic design of the controller of autonomous agents, described as a finite-state machine.  The application of this method to well-known problems, for example the follow-up of a trail or the resolution of a maze, led to the emergence of some behaviors we could qualify as intelligent. Moreover, it is possible to use the method in a hierarchical way in order to obtain complex behaviors starting from a set of basic actions. We have used an algorithm which is a variation of reinforcement learning with a reward adapted to the degree of uncertainty of the performed prediction.



Russell Standish
2002-11-13