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

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

9 February 2024

Praveen Palanisamy

Kalyan Shankar Basu

Furong Huang

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

4 / 4 papers shown

Title
PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control Ruijie Zheng Ching-An Cheng Hal Daumé Furong Huang Andrey Kolobov 19 9 0 16 Feb 2024
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL Xiyao Wang Ruijie Zheng Yanchao Sun Ruonan Jia Wichayaporn Wongkamjan Huazhe Xu Furong Huang OffRL 49 12 0 11 Oct 2023
Masked World Models for Visual Control Younggyo Seo Danijar Hafner Hao Liu Fangchen Liu Stephen James Kimin Lee Pieter Abbeel OffRL 77 144 0 28 Jun 2022
Decoupling Representation Learning from Reinforcement Learning Adam Stooke Kimin Lee Pieter Abbeel Michael Laskin SSL DRL 261 337 0 14 Sep 2020