Masked Imitation Learning: Discovering Environment-Invariant Modalities in Multimodal Demonstrations
Yilun Hao,Ruinan Wang,Zhangjie Cao,Zihan Wang,Yuchen Cui,Dorsa Sadigh,Yilun Hao,Ruinan Wang,Zhangjie Cao,Zihan Wang,Yuchen Cui,Dorsa Sadigh
Multimodal demonstrations provide robots with an abundance of information to make sense of the world. However, such abundance may not always lead to good performance when it comes to learning sensorimotor control policies from human demonstrations. Extraneous data modalities can lead to state over-specification, where the state contains modalities that are not only useless for decision-making but ...
