Papers › Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control

Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control

25 May 2024arXiv:2405.16158archive 2025-07-28

Michal Nauman, Mateusz Ostaszewski, Krzysztof Jankowski, Piotr Miłoś, Marek Cygan

Sample efficiency in Reinforcement Learning (RL) has traditionally been driven by algorithmic enhancements. In this work, we demonstrate that scaling can also lead to substantial improvements. We conduct a thorough investigation into the interplay of scaling model capacity and domain-specific RL enhancements. These empirical findings inform the design choices underlying our proposed BRO (Bigger, Regularized, Optimistic) algorithm. The key innovation behind BRO is that strong regularization allows for effective scaling of the critic networks, which, paired with optimistic exploration, leads to superior performance. BRO achieves state-of-the-art results, significantly outperforming the leading model-based and model-free algorithms across 40 complex tasks from the DeepMind Control, MetaWorld, and MyoSuite benchmarks. BRO is the first model-free algorithm to achieve near-optimal policies in the notoriously challenging Dog and Humanoid tasks.

PaperPDFCodeCode Syntology ranMethod as code

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.

Syntology holds a reference implementation of BRO, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='BRO') (how to connect); the free check have('2405.16158') needs no token.

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

Code

Syntology 20 code samples harvested from 5 repositories linked to this paper: 11 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 12 samples from 4 repositories, 8 ran (7 with no instrument failure; 1 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

naumix/BiggerRegularizedOptimistic officialmentioned in papermentioned on GitHubjaxSyntology: 8 samples, 3 ran (0 instrument-failed) · 5 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 11 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
7ran
9unverified

Licence: 3 of the 20 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 5 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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

naumix/BiggerRegularizedOptimistic official repository 8 samples, 3 ran (0 instrument-failed) · 5 unverified
Model in 227 papers jaxrl/bro/bro_learner.py ran MIT (permissive) · 60af6b78baad020d · report fixture: returned Model · level recorded 2026-09-22
SaveState jaxrl/bro/bro_learner.py ran · metamorphic tier: deterministic MIT (permissive) · aa4126690e869bbf · report fixture: returned SaveState · level recorded 2026-09-22
huber_replace jaxrl/bro/bro_learner.py ran · violated contract MIT (permissive) · ae8a2984d9e381fd · report fixture: signature td_errors:ArrayImpl/1/float, kappa:float/0/float · returned ArrayImpl · level recorded 2026-09-22
BRO jaxrl/bro/bro_learner.py unverified MIT (permissive) · ce00f81a9f2c68ec · report
_do_multiple_updates jaxrl/bro/bro_learner.py unverified MIT (permissive) · 390709e4e4f378c9 · report
_update jaxrl/bro/bro_learner.py unverified MIT (permissive) · 9e582c32acd1ef30 · report
calculate_quantile_huber_loss jaxrl/bro/bro_learner.py unverified MIT (permissive) · ea6955fd0f62ad14 · report
target_update in 9 papers jaxrl/bro/bro_learner.py unverified MIT (permissive) · ce51f9f65a9e0a89 · report
sfujim/TD3 found in paper text by Syntology 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Actor in 68 papers TD3.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 9c81de6b9c4c134f · report fixture: returned Actor · level recorded 2026-09-22
TD3 TD3.py ran MIT (permissive) · 590f1bfec73e823b · report fixture: returned TD3 · level recorded 2026-09-22
adityab/CrossQ found in paper text by Syntology 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BatchRenorm sbx/sac/policies.py ran licence not identified · pointer only · 78955e8aa0ecd20a · report fixture: returned BatchRenorm · level recorded 2026-09-22
denisyarats/pytorch_sac found in paper text by Syntology 2 samples, 2 ran (1 instrument-failed) · 0 unverified
mlp in 108 papers utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · db00dda8b96201d3 · report fixture: signature input_dim:int/0/int, hidden_dim:int/0/int, output_dim:int/0/int, hidden_depth:int/0/int, output_mod:callable/0/? · returned Sequential · level recorded 2026-09-22
to_np in 63 papers
census: 8 implementations from 14 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 6ee8c9901ab984a9 · report fixture: signature t:Tensor/2/float · returned ndarray · level recorded 2026-09-22
proceduralia/high_replay_ratio_continuous_control found in paper text by Syntology 7 samples, 3 ran (0 instrument-failed) · 4 unverified
Model in 227 papers jaxrl/agents/sac/sac_learner.py ran MIT (permissive) · 8e4b15accbb74070 · report fixture: returned Model · level recorded 2026-09-22
SaveState jaxrl/agents/sac/sac_learner.py ran · metamorphic tier: deterministic MIT (permissive) · cfb82327f2389742 · report fixture: returned SaveState · level recorded 2026-09-22
tree_norm jaxrl/agents/sac/sac_learner.py ran · honoured contract MIT (permissive) · dd6b087dfe582577 · report fixture: signature tree:dict/0/? · returned ArrayImpl · level recorded 2026-09-22
SACLearner jaxrl/agents/sac/sac_learner.py unverified MIT (permissive) · 09d56aa25dec1123 · report
_do_multiple_updates jaxrl/agents/sac/sac_learner.py unverified MIT (permissive) · ed8a594097bbbd78 · report
_update jaxrl/agents/sac/sac_learner.py unverified MIT (permissive) · 1f40e01b920c066f · report
target_update in 9 papers jaxrl/agents/sac/sac_learner.py unverified MIT (permissive) · 804f231f90e60d49 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

5 assemblies on this paper: 4 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for BRO (graph method: BRO), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 4 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_optimistic_q_value entry · level 3 · ran · honoured contract · 8587f19e0f82ec7e5dabb77805adac3bae846f286d367c8d7de93ad5b5a6c874

4 sibling assemblies for BRO (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for BRO (graph method: BRO). 7 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. SACLearner entry · level 0 · unverified · 09d56aa25dec1123
  2. Model helper · level 1 · ran · 8e4b15accbb74070
  3. _do_multiple_updates update_rule · level 0 · unverified · ed8a594097bbbd78
  4. SaveState helper · level 1 · ran · cfb82327f2389742
  5. tree_norm helper · level 1 · ran · honoured contract · dd6b087dfe582577
  6. _update update_rule · level 0 · unverified · 1f40e01b920c066f
  7. target_update helper · level 0 · unverified · 804f231f90e60d49

harvested Assembly for BRO (graph method: BRO). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. TD3 entry · level 1 · ran · 590f1bfec73e823b
  2. Actor model · level 1 · ran · 9c81de6b9c4c134f
  3. Critic model · level 1 · ran · 917266e440b9fbc2

harvested Assembly for BRO (graph method: BRO). 9 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. BRO entry · level 0 · unverified · ce00f81a9f2c68ec
  2. Model helper · level 1 · ran · 60af6b78baad020d
  3. _do_multiple_updates update_rule · level 0 · unverified · 390709e4e4f378c9
  4. SaveState helper · level 1 · ran · aa4126690e869bbf
  5. tree_norm helper · level 1 · ran · honoured contract · dd6b087dfe582577
  6. _update update_rule · level 0 · unverified · 9e582c32acd1ef30
  7. target_update helper · level 0 · unverified · ce51f9f65a9e0a89
  8. calculate_quantile_huber_loss loss · level 0 · unverified · ea6955fd0f62ad14
  9. huber_replace helper · level 1 · ran · violated contract · ae8a2984d9e381fd

harvested Assembly for BRO (graph method: BRO). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. BatchRenorm entry · level 1 · ran · 78955e8aa0ecd20a

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2405.16158") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continuous ControlReinforcement Learning (RL)continuous-control

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