The MATHESIS project aims to explore fundamental aspects of social communication and adaptive behavior, especially the process of assigning meaning to the actions of other subjects. This will be demonstrated by developing and validating artificial cognitive agents, primarily robotic ones, able to acquire a repertory of motor actions by observational learning. Observational learning is understood here as the capacity to acquire an action strategy only through observation of other agents, without the experimentation needed in other learning procedures. Neurophysiological investigations will attempt to establish that the neural representations of action-execution, action-observation and action-recall overlap extensively within the cortex, as suggested by our preliminary results. A major implication of this, both for biological and for artificial agents, is that it should be possible to train their motor system by simple action-observation and action-recall, as in the traditional use of observational learning and mental training (e.g., the use of videotapes to train athletes). The MATHESIS project will assess the generality, scalability, accuracy and robustness of such cognitive architectures. Furthermore, it will establish the developmental stage at which observational learning can be used efficiently in infants and children.