2012
EMSS 2012 Proceeding
Multi-actors distributed control systems: reinforcement signal by shannon?s entropy
Authors: Youcef Zennir, Denis Pomorski
Abstract
This paper presents a multi-actors distributed control systems in an unknown environment. These actors are reactive entities able to react to the stimuli coming from the environment and to choose between several actions. In order to improve their behaviour (i.e. in order to choose the good action) in the course of time, the multi- actors system must be able to use reinforcement learning. This signal of reinforcement is, until now, a signal whose values are previously defined. We propose to raise this technique by using the Shannon?s entropy to measure the coherence of the action choice using the transformation of the reinforcement signal table. This stage, of local training will allow the improvement of the control of the global system and coordination between the various actors. The results of the simulation show that the actor can learn to control its trajectory efficiently.
I3M Scientific Sponsors
I3M Industrial Sponsors
I3M Media Sponsors
