Reinforcement Symbolic Learning

Chloé Mercier (1) , Frédéric Alexandre (1) , Thierry Viéville (1, 2)

1 Mnemosyne - Mnemonic Synergy
2 LINE - Laboratoire d'Innovation et Numérique pour l'Education

Complex problem solving involves representing structured knowledge, reasoning and learning, all at once. In this prospective study, we make explicit how a reinforcement learning paradigm can be applied to a symbolic representation of a concrete problem-solving task, modeled here by an ontology. This preliminary paper is only a set of ideas while feasibility verification is still a perspective of this work.

Mots clés: Reinforcement Symbolic Learning; Ontology Edit Distances; Models for Learning Sciences

Domaines: Intelligence artificielle [cs.AI]; Neurosciences; Education

Chloé Mercier, Frédéric Alexandre, Thierry Viéville. Reinforcement Symbolic Learning. ICANN 2021 - 30th International Conference on Artificial Neural Networks, Sep 2021, Bratislava / Virtual, Slovakia. ⟨hal-03327706⟩