Papers › Visual Reinforcement Learning with Self-Supervised 3D Representations

Visual Reinforcement Learning with Self-Supervised 3D Representations

13 Oct 2022arXiv:2210.07241archive 2025-07-28

Yanjie Ze, Nicklas Hansen, Yinbo Chen, Mohit Jain, Xiaolong Wang

A prominent approach to visual Reinforcement Learning (RL) is to learn an internal state representation using self-supervised methods, which has the potential benefit of improved sample-efficiency and generalization through additional learning signal and inductive biases. However, while the real world is inherently 3D, prior efforts have largely been focused on leveraging 2D computer vision techniques as auxiliary self-supervision. In this work, we present a unified framework for self-supervised learning of 3D representations for motor control. Our proposed framework consists of two phases: a pretraining phase where a deep voxel-based 3D autoencoder is pretrained on a large object-centric dataset, and a finetuning phase where the representation is jointly finetuned together with RL on in-domain data. We empirically show that our method enjoys improved sample efficiency in simulated manipulation tasks compared to 2D representation learning methods. Additionally, our learned policies transfer zero-shot to a real robot setup with only approximate geometric correspondence, and successfully solve motor control tasks that involve grasping and lifting from a single, uncalibrated RGB camera. Code and videos are available at https://yanjieze.com/3d4rl/ .

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 17 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 1 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: 17 samples from 1 repository, 16 ran (11 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

YanjieZe/rl3d officialmentioned on GitHubpytorchMITSyntology: 17 samples, 16 ran (5 instrument-failed) · 1 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

17 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 1 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.

4ran · our draft was wrong
1ran; the contract check could not run
11ran
1unverified

Licence: 2 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, 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 YanjieZe/rl3d. “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.

YanjieZe/rl3d official repository 17 samples, 16 ran (5 instrument-failed) · 1 unverified
cat in 32 papers src/utils.py ran fingerprinted MIT (permissive) · 6c2c84b4ccb7f17b · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, axis:int/0/int · returned Tensor · level recorded 2026-09-24
conv in 178 papers src/algorithms/modules_3d.py ran MIT (permissive) · 64155049b60f0d6b · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:int/0/int · returned Sequential · level recorded 2026-09-25
euler2mat in 21 papers src/algorithms/rot_utils.py ran MIT (permissive) · 797689fffbce98da · report fixture: signature angle:Tensor/2/float, scaling:bool/0/bool, translation:bool/0/bool · returned Tensor · level recorded 2026-09-25
gaussian_logprob in 17 papers src/algorithms/modules.py ran · our draft was wrong fingerprinted MIT (permissive) · 2df17488b927be0b · report fixture: signature noise:Tensor/2/float, log_std:Tensor/2/float · returned Tensor · level recorded 2026-09-24
hsv2rgb in 5 papers src/color_jitter.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 718e1902f65f1be2 · report fixture: signature hsv:Tensor/4/float · returned Tensor · level recorded 2026-09-22
load_config in 389 papers src/utils.py ran MIT (permissive) · 5912a589c21e0e7f · report fixture: signature key:NoneType/0/? · returned dict · level recorded 2026-09-26
make_dir in 27 papers src/utils.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
prefill src/algorithms/per.py ran fingerprinted MIT (permissive) · a935467503363d78 · report fixture: signature arr:ndarray/2/float, chunk_size:int/0/int · returned ndarray · level recorded 2026-09-25
prefill_memory src/algorithms/per.py ran MIT (permissive) · 8cb3ce3c5bb986f0 · report fixture: signature capacity:int/0/int, obs_shape:tuple/1/int · returned ndarray · level recorded 2026-09-25
quat2euler src/algorithms/rot_utils.py ran MIT (permissive) · a0a7fcf830f831b6 · report fixture: signature x:float/0/float, y:float/0/float, z:float/0/float, w:float/0/float · returned tuple · level recorded 2026-09-25
quat2mat in 26 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/algorithms/rot_utils.py ran MIT (permissive) · 86eaf46a4e1b7005 · report fixture: signature quat:Tensor/2/float, scaling:bool/0/bool, translation:bool/0/bool · returned Tensor · level recorded 2026-09-25
random_conv src/augmentations.py ran fingerprinted MIT (permissive) · 0604211861b8f1e9 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-25
rgb2hsv src/color_jitter.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 1c24bb2fb72c4f9d · report fixture: signature rgb:Tensor/4/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
squash in 30 papers
census: 8 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
src/algorithms/modules.py ran · our draft was wrong fingerprinted MIT (permissive) · 121cb336a1e1278a · report fixture: signature mu:Tensor/2/float, pi:Tensor/2/float, log_pi:Tensor/2/float · returned tuple · level recorded 2026-09-24
stn src/algorithms/modules_3d.py ran MIT (permissive) · 8ec40d7c6f748f4e · report fixture: signature x:Tensor/4/float, theta:Tensor/3/float, padding_mode:str/0/str · returned Tensor · level recorded 2026-09-25
xavier_uniform_init src/algorithms/modules.py ran MIT (permissive) · c71774582015fd4b · report fixture: signature module:callable/0/?, gain:float/0/float · returned Linear · level recorded 2026-09-25
visual_representation load_3d.py unverified MIT (permissive) · 05f8b4749415d195 · report

Tasks

Reinforcement LearningReinforcement Learning (RL)Representation LearningSelf-Supervised Learningreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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