Skip to Main content Skip to Navigation

Intrinsically Motivated and Interactive Reinforcement Learning: a Developmental Approach

Abstract : Reinforcement learning (RL) is today more popular than ever, but certain basic skills are still out of reach of this paradigm: object manipulation, sensorimotor control, natural interaction with other agents. A possible approach to address these challenges consist in taking inspiration from human development, or even trying to reproduce it. In this thesis, we study the intersection of two crucial topics in developmental sciences and how to apply them to RL in order to tackle the aforementioned challenges: interactive learning and intrinsic motivation. Interactive learning and intrinsic motivation have already been studied, separately, in combination with RL, but in order to improve quantitatively existing agents performances, rather than to learn in a developmental fashion. We thus focus our efforts on the developmental aspect of these subjects. Our work touches the self-organisation of learning in developmental trajectories through an intrinsically motivated for learning progress, and the interaction of this organisation with goal-directed learning and imitation learning. We show that these mechanisms, when implemented in open-ended environments with no task predefined, can interact to produce learning behaviors that are sound from a developmental standpoint, and richer than those produced by each mechanism separately.
Complete list of metadatas

Cited literature [232 references]  Display  Hide  Download
Contributor : Pierre Fournier <>
Submitted on : Tuesday, January 7, 2020 - 12:57:07 PM
Last modification on : Friday, January 10, 2020 - 1:43:27 AM


Files produced by the author(s)


  • HAL Id : tel-02425013, version 1


Pierre Fournier. Intrinsically Motivated and Interactive Reinforcement Learning: a Developmental Approach. Artificial Intelligence [cs.AI]. EDITE de Paris, 2019. English. ⟨tel-02425013⟩



Record views


Files downloads