Papers › A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning

A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning

27 May 2024arXiv:2405.17416archive 2025-07-28

Abdulaziz Almuzairee, Nicklas Hansen, Henrik I. Christensen

Q-learning algorithms are appealing for real-world applications due to their data-efficiency, but they are very prone to overfitting and training instabilities when trained from visual observations. Prior work, namely SVEA, finds that selective application of data augmentation can improve the visual generalization of RL agents without destabilizing training. We revisit its recipe for data augmentation, and find an assumption that limits its effectiveness to augmentations of a photometric nature. Addressing these limitations, we propose a generalized recipe, SADA, that works with wider varieties of augmentations. We benchmark its effectiveness on DMC-GB2 - our proposed extension of the popular DMControl Generalization Benchmark - as well as tasks from Meta-World and the Distracting Control Suite, and find that our method, SADA, greatly improves training stability and generalization of RL agents across a diverse set of augmentations. For visualizations, code and benchmark: see https://aalmuzairee.github.io/SADA/

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 2 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (8 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 13 samples that ran has no recorded date.

aalmuzairee/dmcgb2 officialmentioned on GitHubpytorchMITSyntology: 15 samples, 13 ran (5 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 2 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
2ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
3ran
2unverified

Licence: 1 of the 15 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from aalmuzairee/dmcgb2. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

aalmuzairee/dmcgb2 official repository 15 samples, 13 ran (5 instrument-failed) · 2 unverified
blend_to_background envs/dcs/background.py ran MIT (permissive) · aaac25ec971b783a · report fixture: signature alpha:float/0/float, image:ndarray/3/int, background:ndarray/3/int · returned ndarray · level recorded 2026-09-24
cfg_to_group in 5 papers logger.py ran MIT (permissive) · b4c7211e3a57cfee · report fixture: signature cfg:Config/0/?, return_list:bool/0/bool · returned str · level recorded 2026-09-24
count_parameters in 278 papers utils.py ran · honoured contract MIT (permissive) · f6b944f50d3f15ae · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
episode_len in 14 papers replay_buffer.py ran · honoured contract MIT (permissive) · 9f840a22d31a89bc · report fixture: signature episode:dict/0/? · returned int · level recorded 2026-09-24
eul2mat envs/dcs/camera.py ran · violated contract fingerprinted MIT (permissive) · 1caf35263b273c65 · report fixture: signature theta:ndarray/1/float · returned ndarray · level recorded 2026-09-24
get_lookat_xmat_no_roll envs/dcs/camera.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · c9e0d5556a3efb6d · report fixture: signature agent_pos:ndarray/1/float, camera_pos:ndarray/1/float · returned ndarray · level recorded 2026-09-24
imread in 54 papers envs/dcs/background.py ran · honoured contract MIT (permissive) · 0a27d3f938cef78f · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-24
load_episode in 15 papers replay_buffer.py ran · our draft was wrong MIT (permissive) · 184876e5f4ab6562 · report fixture: signature fn:PosixPath/0/? · returned dict · level recorded 2026-09-24
make_dir in 27 papers logger.py ran · our draft was wrong fingerprinted MIT (permissive) · 1ac4e5bffc3dbbd3 · report fixture: signature dir_path:str/0/str · returned str · level recorded 2026-09-24
make_replay_loader in 11 papers replay_buffer.py ran · our draft was wrong MIT (permissive) · d4c61f80049c6885 · report fixture: signature replay_dir:PosixPath/0/?, max_size:int/0/int, batch_size:int/0/int, num_workers:int/0/int, save_snapshot:bool/0/bool, nstep:int/0/int, discount:float/0/float · returned DataLoader · level recorded 2026-09-24
rotvec2mat envs/dcs/camera.py ran · violated contract MIT (permissive) · f8a9fb08b89a7e4c · report fixture: signature theta:float/0/float, vec:ndarray/1/float · returned ndarray · level recorded 2026-09-24
size_and_flatten envs/dcs/background.py ran MIT (permissive) · 734ad0bf6105007e · report fixture: signature image:ndarray/3/int, ref_height:int/0/int, ref_width:int/0/int · returned ndarray · level recorded 2026-09-24
to_torch in 53 papers
census: 5 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 6244e9922f4e0610 · report fixture: signature xs:tuple/1/list, device:str/0/str · returned tuple · level recorded 2026-09-22
get_aug in 5 papers augmentations.py unverified MIT (permissive) · 142b53587e010b46 · report
print_run logger.py unverified MIT (permissive) · 65307c94c6e54d43 · report

Tasks

Data AugmentationQ-LearningReinforcement Learningreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections