Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss.

Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Shuang Ma, Hal Daum III, Huazhe Xu, John Langford, Praveen Palanisamy, Kalyan Shankar Basu, Furong Huang

Browse the full ICML paper archive.