A Reinforcement Learning agent learns to inhabit and move an animal-like virtual body. The performance optimisation process takes several days and includes millions of steps, as the model progresses from incapability to competence. These machine behaviours are then transferred onto 3D scans of real people. Finally, a second RL software agent analyses the behaviour and mixes movement in real-time according to abstract aesthetic goals. This results in the breakdown of performance - instead a disjointed and sometimes impossible sequence of body motion appears. A live deconstruction of the goal-seeking impulse, at once relatable and alienating. The real-time dynamic artworks can run in perpetuity.
More Half Cheetah