Papers › Revisiting the Minimalist Approach to Offline Reinforcement Learning

Revisiting the Minimalist Approach to Offline Reinforcement Learning

16 May 2023NeurIPS 2023 11arXiv:2305.09836archive 2025-07-28

Denis Tarasov, Vladislav Kurenkov, Alexander Nikulin, Sergey Kolesnikov

Recent years have witnessed significant advancements in offline reinforcement learning (RL), resulting in the development of numerous algorithms with varying degrees of complexity. While these algorithms have led to noteworthy improvements, many incorporate seemingly minor design choices that impact their effectiveness beyond core algorithmic advances. However, the effect of these design choices on established baselines remains understudied. In this work, we aim to bridge this gap by conducting a retrospective analysis of recent works in offline RL and propose ReBRAC, a minimalistic algorithm that integrates such design elements built on top of the TD3+BC method. We evaluate ReBRAC on 51 datasets with both proprioceptive and visual state spaces using D4RL and V-D4RL benchmarks, demonstrating its state-of-the-art performance among ensemble-free methods in both offline and offline-to-online settings. To further illustrate the efficacy of these design choices, we perform a large-scale ablation study and hyperparameter sensitivity analysis on the scale of thousands of experiments.

PaperPDFConference PDFCodeCode 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 16 code samples harvested from 3 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 15 samples from 2 repositories, 14 ran (8 with no instrument failure; 6 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. 3 of the 15 samples that ran have no recorded date.

dt6a/rebrac officialmentioned in paperjaxSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
adamjelley/efficientofflinerl mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 12 ran (6 instrument-failed) · 0 unverified report
takuseno/d3rlpy mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 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

16 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 6 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.

2ran · honoured contract
2ran · our draft was wrong
4ran; the contract check could not run
7ran
1unverified

Licence: 1 of the 16 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

dt6a/rebrac official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
return_reward_range src/algorithms/rebrac_torch_vis.py ran · honoured contract Apache-2.0 (permissive) · 136a4348dc060901 · report fixture: signature dataset:dict/0/?, max_episode_steps:int/0/int · returned tuple · level recorded 2026-09-22
adamjelley/efficientofflinerl community (archive-listed) 12 samples, 12 ran (6 instrument-failed) · 0 unverified
compute_mean_std in 20 papers algorithms/any_percent_bc.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 4e08ac58e3891cfb · report fixture: signature states:ndarray/2/float, eps:float/0/float · returned tuple · level recorded, date not recorded
compute_mean_std in 20 papers algorithms/iql.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 639b4986c270df90 · report fixture: signature states:ndarray/2/float, eps:float/0/float · returned tuple · level recorded, date not recorded
discount_cumsum in 35 papers
census: 6 implementations from 13 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
algorithms/cql.py ran Apache-2.0 (permissive) · d0c4a0aa6c8b23c1 · report fixture: signature x:ndarray/1/float, discount:float/0/float, include_first:bool/0/bool · returned ndarray · level recorded 2026-09-24
discount_cumsum in 35 papers
census: 6 implementations from 13 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
algorithms/edac.py ran Apache-2.0 (permissive) · 04ad4ada1fd13ab2 · report fixture: signature x:Tensor/1/float, discount:float/0/float, include_first:bool/0/bool · returned Tensor · level recorded 2026-09-24
discount_cumsum in 35 papers
census: 6 implementations from 13 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
algorithms/sac_n.py ran fingerprinted Apache-2.0 (permissive) · e258d5be5c961c7a · report fixture: signature x:ndarray/1/float, discount:float/0/float · returned ndarray · level recorded 2026-09-24
discounted_cumsum algorithms/dt.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · f1082bd682dc3cf0 · report fixture: signature x:ndarray/1/float, gamma:float/0/float · returned ndarray · level recorded 2026-09-24
normalize_states in 15 papers algorithms/any_percent_bc.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · ba80f9ff81b1de5f · report fixture: signature states:ndarray/2/float, mean:ndarray/1/float, std:ndarray/1/float · returned ndarray · level recorded, date not recorded
pad_along_axis in 6 papers algorithms/dt.py ran Apache-2.0 (permissive) · 47482b0dd3325c35 · report fixture: signature arr:ndarray/2/float, pad_to:int/0/int, axis:int/0/int, fill_value:float/0/float · returned ndarray · level recorded 2026-09-24
wrap_env in 9 papers algorithms/awac.py ran Apache-2.0 (permissive) · 80f4da28d1c7ef4f · report fixture: signature env:TimeLimit/0/?, state_mean:ndarray/1/float, state_std:ndarray/1/float · returned TransformObservation · level recorded 2026-09-25
wrap_env in 9 papers algorithms/any_percent_bc.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 4dd56ecf0f797666 · report fixture: signature env:TimeLimit/0/?, state_mean:ndarray/1/float, state_std:ndarray/1/float, reward_scale:float/0/float · returned TransformReward · level recorded 2026-09-25
wrap_env in 9 papers algorithms/iql.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · a8341f5e34d50ae6 · report fixture: signature env:TimeLimit/0/?, state_mean:ndarray/1/float, state_std:ndarray/1/float, reward_scale:float/0/float · returned TransformReward · level recorded 2026-09-25
wrap_env in 9 papers algorithms/dt.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 637dc1e936615e64 · report fixture: signature env:TimeLimit/0/?, state_mean:ndarray/1/float, state_std:ndarray/1/float, reward_scale:float/0/float · returned TransformReward · level recorded 2026-09-24
takuseno/d3rlpy community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
asdict_as_float d3rlpy/dataclass_utils.py ran MIT (permissive) · 041f98fc8573d532 · report fixture: signature obj:SampleDataClass/0/? · returned dict · level recorded 2026-09-26
asdict_without_copy d3rlpy/dataclass_utils.py ran MIT (permissive) · 42fee5768773ac46 · report fixture: signature obj:SampleDataclass/0/? · returned dict · level recorded 2026-09-26
init_process_group d3rlpy/distributed.py unverified MIT (permissive) · 027b4e46e81ee939 · report

Tasks

D4RLOffline RLReinforcement LearningReinforcement Learning (RL)reinforcement-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