Intrinsic Motivations for Forming Actions and Producing Goal Directed Behaviour

Abstract

In classical reinforcement learning framework, an external, handcrafted reward typically drives the learning process. Intrinsically motivated systems, on the other hand, can guide their learning process autonomously by computing the interest they have in each task they can engage in. We explore how intrinsic motivation could be implemented in the iCub platform on a learning task that was used previously with infants and monkeys, with a focus on discriminating between task of varying difficulty, and observing how their interest towards the tasks change as their knowledge of them progresses. Two main different approaches were taken : one where the reinforcement learning framework was adapted to an intrinsic reward, and another where the focus was put on a goal-oriented architecture. Two experiments settings were used, one with a console proposing buttons that activated boxes, and another proposing an interaction with rods : both experiments exhibited two tasks, one easy, and one difficult to learn. In each experiment, the system is able to successfully focus on learning the easier task earlier than the difficult one.