Work in progress: A Reinforcement Learning AI agent learns to control a quadruped body from scratch. The performance optimisation process takes several days and includes millions of steps, as the model progresses from incapability to competence. These behaviours are then transferred onto 3D scans of real humans, which are ‘re-skinned’ with metal, stone and other materials. Finally, a second AI agent breaks down the linear progression in performance and re-orders movement according to its own aesthetic goals, resulting in a variety of different behavioural patterns played out in real-time.