MENU

Dr Frédéric Kaplan

2007

Intrinsic Motivation Systems for Autonomous Mental Development

Topics:
Language
Authors
Pierre-Yves Oudeyer , Frédéric Kaplan , Verena Hafner |

IEEE Transactions on Evolutionary Computation, 11, 2, 2007. pp.265--286.

read more

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 Keywords: active learning, autonomy, behavior, complexity, curiosity, sensorimotor development, cognitive development, developmental trajectory, epigenetic robotics, intrinsic motivation, learning, reinforcement learning, values.
2007

Language Evolution as a Darwinian Process: Computational Studies

Topics:
Language
Authors
Pierre-Yves Oudeyer , Frédéric Kaplan |

Cognitive Processing, 8, 1, 2007. pp.21--35.

read more

Abstract

This paper presents computational experiments that illustrate how one can precisely conceptualize language evolution as a Darwinian process. We show that there is potentially a wide diversity of replicating units and replication mechanisms involved in language evolution. Computational experiments allow us to study systemic properties coming out of populations of linguistic replicators: linguistic replicators can adapt to specific external environments; they evolve under the pressure of the cognitive constraints of their hosts, as well as under the functional pressure of communication for which they are used; one can observe neutral drift; coalitions of replicators may appear, forming higher level groups which can themselves become subject to competition and selection.
2006

The progress-drive hypothesis: an interpretation of early imitation

Topics:
Language
Authors
Frédéric Kaplan , Pierre-Yves Oudeyer |

Models and mechanisms of imitation and social learning: Behavioural, social and communication dimensions, edited by:Dautenhahn, K. and Nehaniv, C., Cambridge University Press, 2006.

2006

Discovering Communication

Topics:
Language
Authors
Pierre-Yves Oudeyer , Frédéric Kaplan |

Connection Science, 18, 2, 2006. pp.189--206.

2002

Bootstrapping grounded word semantics

Topics:
Language
Authors
Luc Steels , Frédéric Kaplan |

Linguistic evolution through language acquisition: formal and computational models, edited by:Briscoe, T., Cambridge University Press, Cambridge, UK, 2002. pp.53--74.

read more

Abstract

The paper reports on experiments with a population of visually grounded robotic agents capable of bootstrapping their own ontology and shared lexicon without prior design nor other forms of human intervention. The agents do so while playing a particular language game called the guessing game. We show that synonymy and ambiguity arise as emergent properties in the lexicon, due to the situated grounded character of the agent-environment interaction, but that there are also tendencies to dampen them so as to make the language more coherent and thus more optimal from the viewpoints of communicative success, cognitive complexity, and learnability.
2002

Crucial factors in the origins of word-meaning

Topics:
Language
Authors
Luc Steels , Frédéric Kaplan , Angus McIntyre , Joris Van Looveren |

The Transition to Language, edited by:Wray, A., Oxford University Press, Oxford, UK, 2002. pp.252--271.

read more

Abstract

We have been conducting large-scale public experiments with artificial robotic agents to explore what the necessary and sufficient prerequisites are for word-meaning pairs to evolve autonomously in a population of agents through a self-organized process. We focus not so much on the question of why language has evolved but rather on how. Our hypothesis is that when agents engage in particular interactive behaviors which in turn require specific cognitive structures, they automatically arrive at a language system. We study this topic by performing experiments based on artificial systems. One such experiment, known as the Talking Heads Experiment, employs a set of visually grounded autonomous robots into which agents can install themselves to play language games with each other.
2001

La naissance d’une langue chez les robots

Topics:
Language
Authors
Frédéric Kaplan |

Hermes Science, Paris, 2001.

2000

AIBO’s first words: The social learning of language and meaning

Topics:
Language
Authors
Luc Steels , Frédéric Kaplan |

Evolution of Communication, 4, 1, 2000. pp.3--32.

2000

Talking AIBO : First experimentation of verbal interactions with an autonomous four-legged robot

Topics:
Language
Authors
Frédéric Kaplan |

Learning to Behave: Interacting agents CELE-TWENTE Workshop on Language Technology, edited by:Nijholt, A. and Heylen, D. and Jokinen, K., October, 2000. pp.57--63.

2000

Crucial factors in the origins of word-meaning

Topics:
Language
Authors
Luc Steels , Frédéric Kaplan , Angus McIntyre , Joris Van Looveren |

Proceedings of The 3rd Evolution of Language Conference, edited by:Dessalles, J-L. and Ghadakpour, L., ENST 2000 S 002, Paris, 2000. pp.214--217.

2000

Origine et ‘evolution du langage : exp’eriences robotiques

Topics:
Language
Authors
Luc Steels , Frédéric Kaplan |

Revue du Palais de la Découverte, 278, May, 2000. pp.63--67.

2000

Semiotic schemata: Selection units for linguistic cultural evolution

Topics:
Language
Authors
Frédéric Kaplan |

Proceedings of Artificial Life VII, edited by:Bedau, M and McCaskill, J. and Packard, N. and Rasmussen, S., The MIT Press, Cambridge, MA, 2000. pp.372--381.

1999

Collective learning and semiotic dynamics

Topics:
Language
Authors
Luc Steels , Frédéric Kaplan |

Advances in Artificial Life: 5th European Conference (ECAL 99), edited by:Floreano, D. and Nicoud, J-D and Mondada, F., Springer-Verlag, Berlin, 1999. pp.679--688.

1999

Amorc{c}age d’une s’emantique lexicale dans une population d’agents autonomes, ancr’es et situ’es

Topics:
Language
Authors
Luc Steels , Frédéric Kaplan |

Traitement automatique du langage naturel 1999, edited by:Amsili, P., Cargèse, Corse, 1999. pp.393--398.

1999

Situated Grounded Word Semantics

Topics:
Language
Authors
Luc Steels , Frédéric Kaplan |

Proceedings of the 16th International Joint Conference on Artificial Intelligence IJCAI 99, edited by:Dean, T., 2, Morgan Kaufmann Publishers, San Francisco, 1999. pp.862-867.

1998

A New Approach to Class Formation in Multi-Agent Simulations of Language Evolution

Topics:
Language
Authors
Frédéric Kaplan |

Proceedings of the third international conference on multi-agent systems (ICMAS 98), edited by:Demazeau, Y., IEEE Computer Society, Los Alamitos, CA, 1998. pp.158--165.

1998

Stochasticity as a Source of Innovation in Language Games

Topics:
Language
Authors
Luc Steels , Frédéric Kaplan |

Proceedings of Artificial Life VI, edited by:Adami, C. and Belew, R. and Kitano, H. and Taylor, C., The MIT Press, Cambridge, MA, June, 1998. pp.368--376.