Papers › Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning

Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning

29 Sep 2023arXiv:2309.16984archive 2025-07-28

Zihan Ding, Chi Jin

Score-based generative models like the diffusion model have been testified to be effective in modeling multi-modal data from image generation to reinforcement learning (RL). However, the inference process of diffusion model can be slow, which hinders its usage in RL with iterative sampling. We propose to apply the consistency model as an efficient yet expressive policy representation, namely consistency policy, with an actor-critic style algorithm for three typical RL settings: offline, offline-to-online and online. For offline RL, we demonstrate the expressiveness of generative models as policies from multi-modal data. For offline-to-online RL, the consistency policy is shown to be more computational efficient than diffusion policy, with a comparable performance. For online RL, the consistency policy demonstrates significant speedup and even higher average performances than the diffusion policy.

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 consistency policy, 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='consistency policy') (how to connect); the free check have('2309.16984') needs no token.

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

Code

Syntology 11 code samples: 10 from 3 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 11: 9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community: 5 samples from 2 repositories, 5 ran (2 with no instrument failure; 3 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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. 6 of the 9 samples that ran have no recorded date.

quantumiracle/consistency_model_for_reinforcement_learning officialmentioned in papermentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 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

11 samples harvested: 9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 3 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 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.

3ran · honoured contract
3ran; the contract check could not run
3ran
2unverified

Licence: 1 of the 11 samples is pointer only, meaning Syntology does not serve that copy's text. 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. 1 sample is listed last, in a group without a repository. “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.

quantumiracle/consistency_model_for_reinforcement_learning official repository 5 samples, 3 ran (0 instrument-failed) · 2 unverified
Consistency agents/consistency.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · dead3c2b85bf0fc2 · report fixture: returned Consistency · level recorded 2026-09-22
WeightedL1 in 8 papers agents/consistency.py ran fingerprinted Apache-2.0 (permissive) · a195e5fbb1ffc8f2 · report fixture: signature pred:Tensor/2/float, targ:Tensor/2/float, weights:Tensor/2/float, take_mean:bool/0/bool · returned Tensor · level recorded 2026-09-24
WeightedL2 in 8 papers agents/consistency.py ran fingerprinted Apache-2.0 (permissive) · 04bd445ebe6af984 · report fixture: signature pred:Tensor/2/float, targ:Tensor/2/float, weights:Tensor/2/float, take_mean:bool/0/bool · returned Tensor · level recorded 2026-09-24
WeightedHuber agents/consistency.py unverified Apache-2.0 (permissive) · c6104b52f96f7bc9 · report
WeightedLoss in 7 papers agents/consistency.py unverified Apache-2.0 (permissive) · 0749c0edc53a9387 · report
Aaditya-Prasad/consistency-policy community 3 samples, 3 ran (3 instrument-failed) · 0 unverified
append_dims in 30 papers
census: 3 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
consistency_policy/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 465f0a6ce0f5e20e · report fixture: signature x:Tensor/2/float, target_dims:int/0/int · returned Tensor · level recorded, date not recorded
euler_to_quat consistency_policy/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · eef3fefaf1daa0fb · report fixture: signature euler:ndarray/2/float, degrees:bool/0/bool · returned ndarray · level recorded, date not recorded
reduce_dims consistency_policy/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · f2143ca43f9dc693 · report fixture: signature x:Tensor/4/float, target_dims:int/0/int · returned Tensor · level recorded, date not recorded
alexander-soare/consistency_policy community 2 samples, 2 ran (0 instrument-failed) · 0 unverified
sample_n_stratified consistency_policy/consistency_model.py ran · honoured contract MIT (permissive) · 0ddc75bcecc6e03f · report fixture: signature batch_size:int/0/int, N:int/0/int, n_strata:int/0/int, device:device/0/? · returned Tensor · level recorded, date not recorded
sample_n_uniform consistency_policy/consistency_model.py ran · honoured contract MIT (permissive) · c9631ffcefa55af9 · report fixture: signature batch_size:int/0/int, N:int/0/int, device:device/0/? · returned Tensor · level recorded, date not recorded
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
linear_schedule in 26 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 4c60d8998b722013 · report fixture: signature start_e:float/0/float, end_e:float/0/float, duration:int/0/int, t:int/0/int · returned float · level recorded, date not recorded

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". 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.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for consistency policy (graph method: consistency policy), 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; 5 property tests passed on both).

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

  1. double_q_loss entry · level 3 · ran · honoured contract · c3e9ea69074e3df3e29ab25554fc67b327fa379e6ea0fbfddcc213c7dd475d31

harvested Assembly for consistency policy (graph method: consistency policy). 5 bricks; individually on a fixture: 3 ran (of which 1 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) · 2 unverified. The assembly has not been run end-to-end.

  1. Consistency entry · level 1 · ran · dead3c2b85bf0fc2
  2. WeightedLoss helper · level 0 · unverified · 0749c0edc53a9387
  3. WeightedHuber helper · level 0 · unverified · c6104b52f96f7bc9
  4. WeightedL1 helper · level 1 · ran · a195e5fbb1ffc8f2
  5. WeightedL2 helper · level 1 · ran · 04bd445ebe6af984

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="2309.16984") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image GenerationOffline RLReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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