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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Ruijie, Liang, Yongyuan, Wang, Xiyao, Ma, Shuang, Daumé III, Hal, Xu, Huazhe, Langford, John, Palanisamy, Praveen, Basu, Kalyan Shankar, Huang, Furong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911885438222336
author Zheng, Ruijie
Liang, Yongyuan
Wang, Xiyao
Ma, Shuang
Daumé III, Hal
Xu, Huazhe
Langford, John
Palanisamy, Praveen
Basu, Kalyan Shankar
Huang, Furong
author_facet Zheng, Ruijie
Liang, Yongyuan
Wang, Xiyao
Ma, Shuang
Daumé III, Hal
Xu, Huazhe
Langford, John
Palanisamy, Praveen
Basu, Kalyan Shankar
Huang, Furong
contents We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-TACO leverages a subset of multitask offline datasets for pretraining a general feature representation, which captures critical environmental dynamics and is fine-tuned using minimal expert demonstrations. It advances the temporal action contrastive learning (TACO) objective, known for state-of-the-art results in visual control tasks, by incorporating a novel negative example sampling strategy. This strategy is crucial in significantly boosting TACO's computational efficiency, making large-scale multitask offline pretraining feasible. Our extensive empirical evaluation in a diverse set of continuous control benchmarks including Deepmind Control Suite, MetaWorld, and LIBERO demonstrate Premier-TACO's effectiveness in pretraining visual representations, significantly enhancing few-shot imitation learning of novel tasks. Our code, pretraining data, as well as pretrained model checkpoints will be released at https://github.com/PremierTACO/premier-taco. Our project webpage is at https://premiertaco.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2402_06187
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
Zheng, Ruijie
Liang, Yongyuan
Wang, Xiyao
Ma, Shuang
Daumé III, Hal
Xu, Huazhe
Langford, John
Palanisamy, Praveen
Basu, Kalyan Shankar
Huang, Furong
Machine Learning
Artificial Intelligence
Robotics
We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-TACO leverages a subset of multitask offline datasets for pretraining a general feature representation, which captures critical environmental dynamics and is fine-tuned using minimal expert demonstrations. It advances the temporal action contrastive learning (TACO) objective, known for state-of-the-art results in visual control tasks, by incorporating a novel negative example sampling strategy. This strategy is crucial in significantly boosting TACO's computational efficiency, making large-scale multitask offline pretraining feasible. Our extensive empirical evaluation in a diverse set of continuous control benchmarks including Deepmind Control Suite, MetaWorld, and LIBERO demonstrate Premier-TACO's effectiveness in pretraining visual representations, significantly enhancing few-shot imitation learning of novel tasks. Our code, pretraining data, as well as pretrained model checkpoints will be released at https://github.com/PremierTACO/premier-taco. Our project webpage is at https://premiertaco.github.io.
title Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2402.06187