Building artificial agents able to autonomously learn new skills and to easily adapt in different and complex environments is an important goal for robotics and machine learning. We propose that providing artificial agents with a learning signal that resembles the characteristic of the phasic activations of dopaminergic neurons would be an advancement in the development of more autonomous and versatile systems. In particular, we suggest that the particular composition of such a signal, determined both by intrinsic and extrinsic reinforcements, would be suitable to improve the implementation of cumulative learning. To validate our hypothesis we performed some experiments with a simulated robotic system that has to learn different skills to obtain rewards. We compared different versions of the system varying the composition of the learning signal and we show that only the system that implements our hypothesis is able to reach high performance in the task.
A bio-inspired learning signal for the cumulative learning of different skills
Contributo in atti di convegno
Workshop Italiano di Vita Artificiale e Computazione Evolutiva, 2012. Proceedings. CD-ROM, pp. 1–12, Parma, 20-21 Febbraio 2012