Abstract-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.

Summary Intelligent animals devote much time and energy to exploring and obtaining information, but the underlying mechanisms are poorly understood. We review recent developments on this topic that have emerged from the traditionally separate fields of machine learning, eye movements in natural behavior, and studies of curiosity in psychology and neuroscience. These studies show that exploration may be guided by a family of mechanisms that range from automatic biases toward novelty or surprise, to systematic search for learning progress and information gain in curiosity-driven behavior. In addition, eye movements reflect visual information search in multiple conditions and are amenable for cellular-level investigations, suggesting that the oculomotor system is an excellent model system for understanding information sampling mechanisms.

a b s t r a c tWe introduce the Self-Adaptive Goal Generation Robust Intelligent Adaptive Curiosity (SAGG-RIAC) architecture as an intrinsically motivated goal exploration mechanism which allows active learning of inverse models in high-dimensional redundant robots. This allows a robot to efficiently and actively learn distributions of parameterized motor skills/policies that solve a corresponding distribution of parameterized tasks/goals. The architecture makes the robot sample actively novel parameterized tasks in the task space, based on a measure of competence progress, each of which triggers low-level goal-directed learning of the motor policy parameters that allow to solve it. For both learning and generalization, the system leverages regression techniques which allow to infer the motor policy parameters corresponding to a given novel parameterized task, and based on the previously learnt correspondences between policy and task parameters.We present experiments with high-dimensional continuous sensorimotor spaces in three different robotic setups: (1) learning the inverse kinematics in a highly-redundant robotic arm, (2) learning omnidirectional locomotion with motor primitives in a quadruped robot, and (3) an arm learning to control a fishing rod with a flexible wire. We show that (1) exploration in the task space can be a lot faster than exploration in the actuator space for learning inverse models in redundant robots; (2) selecting goals maximizing competence progress creates developmental trajectories driving the robot to progressively focus on tasks of increasing complexity and is statistically significantly more efficient than selecting tasks randomly, as well as more efficient than different standard active motor babbling methods; (3) this architecture allows the robot to actively discover which parts of its task space it can learn to reach and which part it cannot.

Intrinsic motivation, centrally involved in spontaneous exploration and curiosity, is a crucial concept in developmental psychology. It has been argued to be a crucial mechanism for open-ended cognitive development in humans, and as such has gathered a growing interest from developmental roboticists in the recent years. The goal of this paper is threefold. First, it provides a synthesis of the different approaches of intrinsic motivation in psychology. Second, by interpreting these approaches in a computational reinforcement learning framework, we argue that they are not operational and even sometimes inconsistent. Third, we set the ground for a systematic operational study of intrinsic motivation by presenting a formal typology of possible computational approaches. This typology is partly based on existing computational models, but also presents new ways of conceptualizing intrinsic motivation. We argue that this kind of computational typology might be useful for opening new avenues for research both in psychology and developmental robotics.Keywords: intrinsic motivation, cognitive development, reward, reinforcement learning, exploration, curiosity, computational modeling, artifi cial intelligence, developmental robotics INTRODUCTIONThere exists a wide diversity of motivation systems in living organisms, and humans in particular. For example, there are systems that push the organism to maintain certain levels of chemical energy, involving the ingestion of food, or systems that push the organism to maintain its temperature or its physical integrity in a zone of viability. Inspired by these kinds of motivation and their understanding by (neuro-) ethologists, roboticists have built machines endowed with similar systems with the aim of providing them with autonomy and properties of life-like intelligence (Arkin, 2005). For example sowbug-inspired robots (Endo and Arkin, 2001), praying mantis robots (Arkin et al., 1998) dog-like robots (Fujita et al., 2001) have been constructed. Some animals, and this is most prominent in humans, also have more general motivations that push them to explore, manipulate or probe their environment, fostering curiosity and engagement in playful and new activities. This kind of motivation, which is called intrinsic motivation by psychologists (Ryan and Deci, 2000), is paramount for sensorimotor and cognitive development throughout lifespan. There is a vast literature in psychology that explains why it is essential for cognitive growth and organization, and investigates the actual potential cognitive processes underlying intrinsic motivation (Berlyne, 1960;Csikszentmihalyi, 1991;Deci and Ryan, 1985;Ryan and Deci, 2000;White, 1959). This has gathered the interest of a growing number of researchers in developmental robotics in the recent years, and several computational models have been developed (see Barto et al., 2004; Oudeyer et al., 2007 for reviews).However, the very concept of intrinsic motivation has never really been consistently and critically discussed from a computational point ...