How Evolution May Work Through Curiosity-Driven Developmental Process

  title={How Evolution May Work Through Curiosity-Driven Developmental Process},
  author={Pierre-Yves Oudeyer and Linda B. Smith},
  journal={Topics in cognitive science},
  volume={8 2},
Infants' own activities create and actively select their learning experiences. Here we review recent models of embodied information seeking and curiosity-driven learning and show that these mechanisms have deep implications for development and evolution. We discuss how these mechanisms yield self-organized epigenesis with emergent ordered behavioral and cognitive developmental stages. We describe a robotic experiment that explored the hypothesis that progress in learning, in and for itself… 

Figures from this paper

Curiosity‐based learning in infants: a neurocomputational approach

It is demonstrated that maximal learning emerges when the model is able to maximize stimulus novelty relative to its internal states, depending on the interaction across learning between the structure of the environment and the plasticity in the learner itself.

Computational Theories of Curiosity-Driven Learning

It is argued that curiosity-driven learning enables organisms to make discoveries to solve complex problems with rare or deceptive rewards, and curiosity can be efficient to bootstrap learning when there is no information about local improvement towards these problems.

A neural network model of curiosity-driven infant categorization

  • Katherine E. TwomeyG. Westermann
  • Computer Science
    2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)
  • 2015
This study provides the first computational investigation of curiosity-based categorization, and points to the importance characterizing development as emerging from the relationship between the learner and its environment.

Computational and Robotic Models of Early Language Development: A Review

Computational and robotics models of early language learning and development are argued to provide concrete theories of language learning as a complex dynamic system, complementing traditional methods in psychology and linguistics.

Proximodistal Exploration in Motor Learning as an Emergent Property of Optimization

This work forms and study computationally the hypothesis that patterns of freezing and freeing of degrees of freedom can emerge spontaneously as the result of a family of stochastic optimization processes, without an innate encoding of a maturational schedule.

Vygotskian Autotelic Artificial Intelligence: Language and Culture Internalization for Human-Like AI

Building autonomous artificial agents able to grow open-ended repertoires of skills across their lives is one of the fundamental goals of AI. To that end, a promising developmental approach recommends

Development of collective behavior in newborn artificial agents

This work bridges the divide between high-dimensional sensory inputs and collective action, resulting in a “pixels-to-actions” model of collective animal behavior.

Intrinsic Rewards in Human Curiosity-Driven Exploration: An Empirical Study

Despite their apparent importance for the acquisition of full-fledged human intelligence, mechanisms of intrinsically motivated autonomous learning are poorly understood. How do humans identify

CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning

CURIOUS is proposed, an algorithm that leverages a modular Universal Value Function Approximator with hindsight learning to achieve a diversity of goals of different kinds within a unique policy and an automated curriculum learning mechanism that biases the attention of the agent towards goals maximizing the absolute learning progress.



Self-organization of early vocal development in infants and machines: the role of intrinsic motivation

A computational model of intrinsically motivated vocal exploration is introduced, which allows the learner to autonomously structure its own vocal experiments, and thus its own learning schedule, through a drive to maximize competence progress.

In Search of the Neural Circuits of Intrinsic Motivation

It is hypothesized that an intrinsic motivation to progress in learning is at the origins of the remarkable structure of children's developmental trajectories and that tonic dopamine acts as a learning progress signal.

Intrinsic Motivation Systems for Autonomous Mental Development

The mechanism of Intelligent Adaptive Curiosity is presented, an intrinsic motivation system which pushes a robot towards situations in which it maximizes its learning progress, thus permitting autonomous mental development.

Discovering communication

A computational model and a robotic experiment are presented to articulate the hypothesis that children discover communication as a result of exploring and playing with their environment and end up being interested by communication through vocal interactions without having a specific drive for communication.

Active Learning and Intrinsically Motivated Exploration in Robots : Advances and Challenges

  • Psychology
  • 2010
L EARNING techniques are increasingly being used in today’s complex robotic systems. Robots are expected to deal with a large variety of tasks using their high-dimensional and complex bodies, to

Intrinsically Motivated Learning in Natural and Artificial Systems

This book introduces the concept of intrinsic motivation in artificial systems, reviews the relevant literature, offers insights from the neural and behavioural sciences, and presents novel tools for research.

Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learner

It is shown that SGIM-ACTS learns significantly more effciently than using single learning strategies, and coherently selects the best strategy with respect to the chosen outcome, taking advantage of the available teachers (with different levels of skills).

On the Impact of Robotics in Behavioral and Cognitive Sciences: From Insect Navigation to Human Cognitive Development

  • P. Oudeyer
  • Psychology
    IEEE Transactions on Autonomous Mental Development
  • 2010
This article presents a series of paradigmatic examples spanning from the modelling of insect navigation, the experimentation of the role of morphology to control locomotion, the development of foundational representations of the body and of the self/other distinction, the self-organization of language in robot societies, and the use of robots as therapeutic tools for children with developmental disorders.

What is Intrinsic Motivation? A Typology of Computational Approaches

This paper sets the ground for a systematic operational study of intrinsic motivation by presenting a formal typology of possible computational approaches, partly based on existing computational models, but also presents new ways of conceptualizing intrinsic motivation.

The progress drive hypothesis: an interpretation of early imitation

Children seem to have a natural tendency to imitate and their interest for particular kinds of imitative behaviour varies greatly with the infant’s age. We argue that different forms of children’s