Perceiving Agent Collaborative Sonic Exploration In Interactive Reinforcement Learning - Laboratoire de recherche en informatique. Équipe: Informatique Centrée sur l'humain Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Perceiving Agent Collaborative Sonic Exploration In Interactive Reinforcement Learning

Résumé

We present the first implementation of a new framework for sound and music computing, which allows humans to explore musical environments by communicating feedback to an artificial agent. It is based on an interactive reinforcement learning workflow, which enables agents to incrementally learn how to act on an environment by balancing exploitation of human feedback knowledge and exploration of new musical content. In a controlled experiment , participants successfully interacted with these agents to reach a sonic goal in two cases of different complexities. Subjective evaluations suggest that the exploration path taken by agents, rather than the fact of reaching a goal, may be critical to how agents are perceived as collaborative. We discuss such quantitative and qualitative results and identify future research directions toward deploying our "co-exploration" approach in real-world contexts.
Fichier principal
Vignette du fichier
smc2018_paper_153_camera_ready.pdf (1.2 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01849074 , version 1 (25-07-2018)

Identifiants

  • HAL Id : hal-01849074 , version 1

Citer

Hugo Scurto, Frédéric Bevilacqua, Baptiste Caramiaux. Perceiving Agent Collaborative Sonic Exploration In Interactive Reinforcement Learning. SMC 2018 - 15th Sound and Music Computing Conference, Jul 2018, Limassol, Cyprus. ⟨hal-01849074⟩
469 Consultations
212 Téléchargements

Partager

Gmail Facebook X LinkedIn More