In this paper, we present goal-discovering robotic architecture for intrisically-motivated learning (GRAIL), a fourlevel architecture that is able to autonomously: 1) discover changes in the environment; 2) form representations of the goals corresponding to those changes; 3) select the goal to pursue on the basis of intrinsic motivations (IMs); 4) select suitable computational resources to achieve the selected goal; 5) monitor the achievement of the selected goal; and 6) self-generate a learning signal when the selected goal is successfully achieved. Building on previous research, GRAIL exploits the power of goals and competence-based IMs to autonomously explore the world and learn different skills that allow the robot to modify the environment. To highlight the features of GRAIL, we implement it in a simulated iCub robot and test the system in four different experimental scenarios where the agent has to perform reaching tasks within a 3-D environment.

Humans and other biological agents are able to autonomously learn and cache different skills in the absence of any biological pressure or any assigned task. In this respect, Intrinsic Motivations (i.e., motivations not connected to reward-related stimuli) play a cardinal role in animal learning, and can be considered as a fundamental tool for developing more autonomous and more adaptive artificial agents. In this work, we provide an exhaustive analysis of a scarcely investigated problem: which kind of IM reinforcement signal is the most suitable for driving the acquisition of multiple skills in the shortest time? To this purpose we implemented an artificial agent with a hierarchical architecture that allows to learn and cache different skills. We tested the system in a setup with continuous states and actions, in particular, with a kinematic robotic arm that has to learn different reaching tasks. We compare the results of different versions of the system driven by several different intrinsic motivation signals. The results show (a) that intrinsic reinforcements purely based on the knowledge of the system are not appropriate to guide the acquisition of multiple skills, and (b) that the stronger the link between the IM signal and the competence of the system, the better the performance.

The first “object” that newborn children play with is their own body. This activity allows them to autonomously form a sensorimotor map of their own body and a repertoire of actions supporting future cognitive and motor development. Here we propose the theoretical hypothesis, operationalized as a computational model, that this acquisition of body knowledge is not guided by random motor-babbling, but rather by autonomously generated goals formed on the basis of intrinsic motivations. Motor exploration leads the agent to discover and form representations of the possible sensory events it can cause with its own actions. When the agent realizes the possibility of improving the competence to re-activate those representations, it is intrinsically motivated to select and pursue them as goals. The model is based on four components: (1) a self-organizing neural network, modulated by competence-based intrinsic motivations, that acquires abstract representations of experienced sensory (touch) changes; (2) a selector that selects the goal to pursue, and the motor resources to train to pursue it, on the basis of competence improvement; (3) an echo-state neural network that controls and learns, through goal-accomplishment and competence, the agent's motor skills; (4) a predictor of the accomplishment of the selected goals generating the competence-based intrinsic motivation signals. The model is tested as the controller of a simulated simple planar robot composed of a torso and two kinematic 3-DoF 2D arms. The robot explores its body covered by touch sensors by moving its arms. The results, which might be used to guide future empirical experiments, show how the system converges to goals and motor skills allowing it to touch the different parts of own body and how the morphology of the body affects the formed goals. The convergence is strongly dependent on competence-based intrinsic motivations affecting not only skill learning and the selection of formed goals, but also the formation of the goal representations themselves.