SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.13649 · 2020

Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels

Rob Fergus, Ilya Kostrikov, Denis Yarats

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 3 have no contract verdict; 1 failure of our instrument; 4 no recorded run), measured 2026-11-21; 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/2004.13649.json · badge: /api/ran/2004.13649.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
xingyu-lin/softagent community
Papers with Code archive
5 ran · 3 no recorded run
YaoMarkMu/DRQTRANS community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
denisyarats/drq marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Encoder Ran
ran on a synthesized input · constructed an object; no result was computed
xingyu-lin/softagent/drq/Drq.py
pointer only (licence: NONE) · get_code("b38de73a34cfe9ce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xingyu-lin/softagent 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.

SquashedNormal Ran
ran on a synthesized input · constructed an object; no result was computed
xingyu-lin/softagent/drq/Drq.py
pointer only (licence: NONE) · get_code("a34dfc7dbdc0905c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xingyu-lin/softagent 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.

TanhTransform Ran
ran on a synthesized input · constructed an object; no result was computed
xingyu-lin/softagent/drq/Drq.py
pointer only (licence: NONE) · get_code("911b6e5c9e17feea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xingyu-lin/softagent 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.

mlp Ran
ran; our contract draft was wrong, not the code
xingyu-lin/softagent/drq/Drq.py
pointer only (licence: NONE) · get_code("bdef24507a4ccfa7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xingyu-lin/softagent 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.

pair Ran
ran, violated the contract we drafted
YaoMarkMu/DRQTRANS/vit.py
code served (permissive licence) · get_code("6ba8cee9f5daea41")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function 'pair' takes a single parameter 't' and returns it as a tuple if it isn't already one
# We need to test both cases: when t is a tuple and when it's not

# Case 1: t is not a tuple (e.g., an integer, string, tensor, etc.)
t_not_tuple = 5

# Case 2: t is already a tuple
t_is_tuple = (3, 7)

# We'll use the non-tuple case as the primary test
ARGS = {
    "t": t_not_tuple
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
to_np Ran
ran, honoured the contract we drafted
xingyu-lin/softagent/drq/Drq.py
pointer only (licence: NONE) · get_code("6ee8c9901ab984a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xingyu-lin/softagent 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.

Actor Not yet run
unverified (harvested, no recorded run)
xingyu-lin/softagent/drq/Drq.py
pointer only (licence: NONE) · get_code("8ad237c6d1f93986")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xingyu-lin/softagent 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.

Critic Not yet run
unverified (harvested, no recorded run)
xingyu-lin/softagent/drq/Drq.py
pointer only (licence: NONE) · get_code("8f4711abca857d4a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xingyu-lin/softagent 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.

DRQAgent Not yet run
unverified (harvested, no recorded run)
xingyu-lin/softagent/drq/Drq.py
pointer only (licence: NONE) · get_code("7626fc3961547410")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xingyu-lin/softagent 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.

DRQAgent Not yet run
unverified (harvested, no recorded run)
denisyarats/drq/drq.py
code served (permissive licence) · get_code("55bfb04404fa6e31")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 5 later) and 5 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
pair 90 other papers
89 later, 1 undated · 8 only as an assembly brick
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2103.15691 (2021-03)
ViViT: A Video Vision Transformer
2103.17239 (2021-03)
Going deeper with Image Transformers
and 87 more not named here
mlp
brick of this paper's assembly: helper
11 other papers
1 dated earlier, 10 later · 2 only as an assembly brick
1812.05905 (2018-12)
Soft Actor-Critic Algorithms and Applications
2110.04935 (2021-10)
Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning
2110.14118 (2021-10)
Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning
and 8 more not named here
to_np
brick of this paper's assembly: helper
9 other papers
1 dated earlier, 8 later · 2 only as an assembly brick
1812.05905 (2018-12)
Soft Actor-Critic Algorithms and Applications
2110.04935 (2021-10)
Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning
2305.16683 (2023-05)
Future-conditioned Unsupervised Pretraining for Decision Transformer
and 6 more not named here
TanhTransform
brick of this paper's assembly: helper
5 other papers
5 later · 4 only as an assembly brick
2209.12016 (2022-09)
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
2210.09598 (2022-10)
Planning for Sample Efficient Imitation Learning
2210.10765 (2022-10)
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
and 2 more not named here
SquashedNormal
brick of this paper's assembly: helper
4 other papers
4 later · 3 only as an assembly brick
2209.12016 (2022-09)
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
2210.09598 (2022-10)
Planning for Sample Efficient Imitation Learning
2210.10765 (2022-10)
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
and 1 more not named here

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 2026-11-21.

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 propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach leverages input perturbations commonly used in computer vision tasks to transform input examples, as well as regularizing the value function and policy. Existing model-free approaches, such as Soft Actor-Critic (SAC) [22], are not able to train deep networks effectively from image pixels. However, the addition of our augmentation method dramatically improves SAC's performance, enabling it to reach state-of-the-art performance on the DeepMind control suite, surpassing model-based [23,38,24] methods and recently proposed contrastive learning [50]. Our approach, which we dub DrQ: Data-regularized Q, can be combined with any model-free reinforcement learning algorithm. We further demonstrate this by applying it to DQN [43] and significantly improve its data-efficiency on the Atari 100k [31] benchmark. An implementation can be found at https://sites. google.com/view/data-regularized-q.

For agents

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

get_harvested_code_for_paper("2004.13649")
get_code_for_paper("2004.13649")
have("2004.13649")

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

curl https://syntology.ai/api/ran/2004.13649.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.13649.svg)](https://syntology.ai/paper/2004.13649)

Connect an agent — have() is free.