This site has been permanently archived. This is a static copy provided by the University of Southampton.
TY - GEN ID - cogprints5473 UR - http://cogprints.org/5473/ A1 - Oudeyer, Pierre-Yves A1 - Kaplan, Fr�d�ric A1 - Hafner, V�r�na TI - Intrinsic Motivation Systems for Autonomous Mental Development Y1 - 2007/// N2 - Exploratory activities seem to be intrinsically rewarding for children and crucial for their cognitive development. Can a machine be endowed with such an intrinsic motivation system? This is the question we study in this paper, presenting a number of computational systems that try to capture this drive towards novel or curious situations. After discussing related research coming from developmental psychology, neuroscience, developmental robotics, and active learning, this paper presents the mechanism of Intelligent Adaptive Curiosity, an intrinsic motivation system which pushes a robot towards situations in which it maximizes its learning progress. This drive makes the robot focus on situations which are neither too predictable nor too unpredictable, thus permitting autonomous mental development.The complexity of the robot?s activities autonomously increases and complex developmental sequences self-organize without being constructed in a supervised manner. Two experiments are presented illustrating the stage-like organization emerging with this mechanism. In one of them, a physical robot is placed on a baby play mat with objects that it can learn to manipulate. Experimental results show that the robot first spends time in situations which are easy to learn, then shifts its attention progressively to situations of increasing difficulty, avoiding situations in which nothing can be learned. Finally, these various results are discussed in relation to more complex forms of behavioral organization and data coming from developmental psychology. Key words: Active learning, autonomy, behavior, complexity, curiosity, development, developmental trajectory, epigenetic robotics, intrinsic motivation, learning, reinforcement learning, values. AV - public KW - Active learning KW - autonomy KW - behavior KW - complexity KW - curiosity KW - development KW - developmental trajectory KW - epigenetic robotics KW - intrinsic motivation KW - learning KW - reinforcement learning KW - values. ER -