Behaviour Aesthetics of Reinforcement Learning in a Robotic Art Installation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Behaviour Aesthetics of Reinforcement Learning in a Robotic Art Installation

Résumé

This paper presents our practice with reinforcement learning (RL) in the context of a robotic art project. We adopted a design-oriented approach to RL, privileging embodied robot behaviours generated by interactive learning processes over offline evaluations of optimal agent policies. We describe aesthetic and technical issues surrounding our experiments with a spheroid robot, and share our reflections on the potential of using RL for behaviour aesthetics.
Fichier principal
Vignette du fichier
audry2020behaviour.pdf (2.96 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03100907 , version 1 (06-01-2021)

Identifiants

  • HAL Id : hal-03100907 , version 1

Citer

Sofian Audry, Rosalie Dumont-Gagné, Hugo Scurto. Behaviour Aesthetics of Reinforcement Learning in a Robotic Art Installation. 4th NeurIPS Workshop on Machine Learning for Creativity and Design, Dec 2020, Vancouver, Canada. ⟨hal-03100907⟩
86 Consultations
70 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More