Motor intelligence involves learning how to maneuver and coordinate a flexible body to solve tasks in a range of complex environments. Such attempts to control physically simulated humanoid bodies come from diverse fields, including computer animation and biomechanics. Recent trends involve hand-crafted objectives, sometimes with motion capture data, and to produce specific behaviors. However, this may require considerable engineering effort, and can result in restricted behaviors or behaviors that may be difficult to repurpose for new tasks.

Google’s Deepmind project exhibits how sophisticated behaviors can emerge from the body interacting with the environment using only simple high-level objectives, such as moving forward without falling. Specifically, Google has trained agents with a variety of simulated bodies to make progress across diverse terrains, which require jumping, turning and crouching. The results show the agents develop these complex skills without receiving specific instructions, an approach that can be applied to train their systems for multiple, distinct simulated bodies.