Third-Person Visual Imitation Learning via
Decoupled Hierarchical Controller
Pratyusha Sharma Deepak Pathak Abhinav Gupta
MIT Facebook AI Research CMU
Abstract
We study a generalized setup for learning from demonstration to build an agent that
can manipulate novel objects in unseen scenarios by looking at only a single video
of human demonstration from a third-person perspective. To accomplish this ...


雷达卡



京公网安备 11010802022788号







