Thanks for joining us for SIGGRAPH 2020. Will we see you at SIGGRAPH 2021?

Technical Paper
:
CARL: Controllable Agent With Reinforcement Learning for Quadruped Locomotion
Event Type
Technical Paper
Registration Levels
US
UA
EU
Time
Location
DescriptionWe present a controller for quadruped characters that follows high-level user intents and naturally interacts with dynamic environments via deep reinforcement learning while preserving natural movements using Generative Adversarial Networks.