SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.06187 · ICML · 2024

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

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

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.06187.json · badge: /api/ran/2402.06187.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
PremierTACO/premier-taco canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
premiertaco/premier-taco canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
choose Ran
ran; our contract draft was wrong, not the code
PremierTACO/premier-taco/replay_buffer.py
pointer only (licence: NONE) · get_code("93768277f8d3a9c3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PremierTACO/premier-taco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

episode_len Ran
ran, honoured the contract we drafted
PremierTACO/premier-taco/replay_buffer.py
pointer only (licence: NONE) · get_code("9f840a22d31a89bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PremierTACO/premier-taco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

expectile_loss Ran
ran; our contract draft was wrong, not the code
PremierTACO/premier-taco/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from orrivlin/implicit-q-learning, is pointer only (licence: NONE) · get_code("f55fa75eaa288304")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PremierTACO/premier-taco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_episode Ran
ran; our contract draft was wrong, not the code
PremierTACO/premier-taco/replay_buffer.py
pointer only (licence: NONE) · get_code("284dd761a9579d78")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PremierTACO/premier-taco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_torch Ran
ran; our contract draft was wrong, not the code
PremierTACO/premier-taco/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from premiertaco/premier-taco, is pointer only (licence: NONE) · get_code("6244e9922f4e0610")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PremierTACO/premier-taco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_torch_distribute Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PremierTACO/premier-taco/utils.py
pointer only (licence: NONE) · get_code("b0eabbe4f3ba312b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PremierTACO/premier-taco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_agent Not yet run
unverified (harvested, no recorded run)
PremierTACO/premier-taco/train_bc.py
pointer only (licence: NONE) · get_code("f1ba293af9a573fd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PremierTACO/premier-taco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

make_agent Not yet run
unverified (harvested, no recorded run)
premiertaco/premier-taco/train_premier_taco_dist.py
pointer only (licence: NONE) · get_code("ff56a87a6c0c857f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, premiertaco/premier-taco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 4 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
to_torch 23 other papers
16 dated earlier, 1 the same month, 6 later · 7 only as an assembly brick
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training
2107.09645 (2021-07)
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
2202.10324 (2022-02)
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
and 20 more not named here
episode_len 12 other papers
5 dated earlier, 1 the same month, 6 later
2107.09645 (2021-07)
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
2211.12740 (2022-11)
Masked Autoencoding for Scalable and Generalizable Decision Making
2302.00965 (2023-02)
Visual Imitation Learning with Patch Rewards
and 9 more not named here
make_agent 4 other papers
3 dated earlier, 1 later
2202.10324 (2022-02)
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
2307.10224 (2023-07)
RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization
2312.17116 (2023-12)
Generalizable Visual Reinforcement Learning with Segment Anything Model
and 1 more not named here
expectile_loss 2 other papers
1 dated earlier, 1 later
2110.06169 (2021-10)
Offline Reinforcement Learning with Implicit Q-Learning
2608.07870 (2026-08)
V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.06187")
get_code_for_paper("2402.06187")
have("2402.06187")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.06187.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.06187.svg)](https://syntology.ai/paper/2402.06187)

Connect an agent — have() is free.