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

Year
2024
Type(s)
Author(s)
Zheng, Ruijie, Yongyuan Liang, Xiyao Wang, Shuang Ma, Hal Daum ́e III, Huazhe Xu, John Langford, Praveen Palanisamy, Kalyan Shankar Basu, Furong Huang.
Source
Proceedings of the 41st International Conference on Machine Learning (ICML), 2024.
BibTeX
BibTeX