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.

翻译：我们提出Premier-TACO，一种面向序列决策任务中提升少样本策略学习效率的多任务特征表征学习方法。该方法利用多任务离线数据集子集预训练通用特征表征，该表征能捕捉关键环境动态特性，并通过极少量专家演示进行微调。本文对视觉控制任务中达到最先进结果的时序动作对比学习（TACO）目标进行改进，引入新型负样本采样策略。该策略在显著提升TACO计算效率方面具有关键作用，使得大规模多任务离线预训练成为可能。我们在Deepmind Control Suite、MetaWorld和LIBERO等多样化连续控制基准上的广泛实证评估表明，Premier-TACO在预训练视觉表征方面具有高效性，显著增强了新任务的少样本模仿学习能力。相关代码、预训练数据及预训练模型检查点将在https://github.com/PremierTACO/premier-taco发布。