« entrain » is an adaptive agent that stimulates social interaction in co-located mobile music-making.

It rewards mobile players with audiovisual effects depending on their individual musical behaviour. An active learning framework, called Bayesian Information Gain, is used to dynamically adapt the rewarding criteria based on the collective musical behavior.

entrain builds on Coloop, an award-winning connected sequencer that allows up to eight mobile users to spontaneously play together by simply accessing a web page. It leverages on soundworks, a JavaScript library for collective mobile web interaction, which supports temporal synchronisation of mobile devices. Current applications investigate how agent adaptation can stimulate social interaction across a diverse range of users, encompassing expert and non-expert musicians.

networked system
interaction design
data design


The project was developed with Abby Wanyu Liu, Benjamin Matuszewski, and Frédéric Bevilacqua in collaboration with the ISMM group of IRCAM, as well as Jean-Louis Fréchin and Uros Petrevski from Nodesign.net, and Norbert Schnell from Collaborative Mobile Music Lab of Furtwangen University, in the context of the Sorbonne Université Doctorate in Computing.

Installation at ACM SIGGRAPH 2019 Studio

Available on GitHub