The team has developed DReCon, a character controller created with the help of deep reinforcement learning. First, simulated human characters learn to move around and balance based on motion capture examples. "Once trained, gamepad controlled characters can be fully simulated using physics and simultaneously directed with a high level of responsiveness at a surprisingly low runtime cost on today’s hardware," states the team.
"Reinforcement learning is used to train a simulated character controller that is general enough to track the entire distribution of motion that can be generated by the kinematic controller. Our design emphasizes responsiveness to user input, visual quality, and low runtime cost for application in video-games," notes the paper's abstract.
