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.
Origine | Fichiers produits par l'(les) auteur(s) |
---|