Agence is a dynamic and interactive film authored by three parties: 1) the director, who establishes the narrative structure and environment, 2) intelligent agents, using reinforcement learning or scripted (hierarchical state machines) AI, and 3) the viewer, who can interact with the system to affect the simulation. We trained RL agents in a multi-agent fashion to control some (or all, based on user choice) of the agents in the film. You can download the game at the Agence website.

This was showcased at the Venice VR film festival this year, and was accepted as an oral at the NeurIPS Machine Learning for Creativity & Design workshop (paper).

Dante Camarena†, Pietro Gagliano, Alexander Bakogeorge, Nicholas Counter, Anuj Patel, Casey Blustein, Erin Ray, David Oppenheim, Laura Mingail, Kory W. Matthewson, Pablo Samuel Castro

Agence visuals

My main involvement with it has been as an “RL advisor”; namely, providing guidance on how to best train the multi-agent system so as to have both capable, interesting, and engaging agents. It’s an ongoing collaborations and is quite likely the most fun out of all my weekly meetings :).

The following video does a great job at explaining more what it’s about.

The Story Behind Agence - A Dynamic Film from Transitional Forms on Vimeo.