SEIL: Simulation-augmented Equivariant Imitation Learning
Mingxi Jia,Dian Wang,Guanang Su,David Klee,Xupeng Zhu,Robin Walters,Robert Platt,Mingxi Jia,Dian Wang,Guanang Su,David Klee,Xupeng Zhu,Robin Walters,Robert Platt
In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine learning tasks. However, image-level data augmentation is insufficient for an imitation learning agent to learn good manipulation policies in a reasonable amount...
