Papers › Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control

Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control

12 Jul 2024arXiv:2407.09024archive 2025-07-28

Huayu Chen, Kaiwen Zheng, Hang Su, Jun Zhu

Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning these policies to align with task-specific annotations like Q-values. This strategy allows us to leverage abundant and diverse behavior data to enhance generalization and enable rapid adaptation to downstream tasks using minimal annotations. In particular, we introduce Efficient Diffusion Alignment (EDA) for solving continuous control problems. EDA utilizes diffusion models for behavior modeling. However, unlike previous approaches, we represent diffusion policies as the derivative of a scalar neural network with respect to action inputs. This representation is critical because it enables direct density calculation for diffusion models, making them compatible with existing LLM alignment theories. During policy fine-tuning, we extend preference-based alignment methods like Direct Preference Optimization (DPO) to align diffusion behaviors with continuous Q-functions. Our evaluation on the D4RL benchmark shows that EDA exceeds all baseline methods in overall performance. Notably, EDA maintains about 95% of performance and still outperforms several baselines given only 1% of Q-labelled data during fine-tuning.

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.

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

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 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: 12 samples from 1 repository, 8 ran (3 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. 3 of the 8 samples that ran have no recorded date.

thu-ml/efficient-diffusion-alignment officialmentioned in papermentioned on GitHubpytorchSyntology: 12 samples, 8 ran (5 instrument-failed) · 4 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

12 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 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.

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

Licence: 12 of the 12 samples are 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 thu-ml/efficient-diffusion-alignment. “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.

thu-ml/efficient-diffusion-alignment official repository 12 samples, 8 ran (5 instrument-failed) · 4 unverified
interpolate_fn in 42 papers dpm_solver_pytorch.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 6a35b62fbc80f70a · report fixture: signature x:Tensor/2/float, xp:Tensor/2/float, yp:Tensor/2/float · returned Tensor · level recorded, date not recorded
asymmetric_l2_loss in 11 papers
census: 4 implementations from 8 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
BDiffusion.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 579d77f78c03773e · report fixture: signature u:Tensor/2/float, tau:float/0/float · returned Tensor · level recorded, date not recorded
expand_dims in 38 papers
census: 6 implementations from 13 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float32
dpm_solver_pytorch.py ran · our draft was wrong no licence file found · pointer only · e6110366588c5c65 · report fixture: signature v:Tensor/1/float, dims:int/0/int · returned Tensor · level recorded, date not recorded
inf_train_gen dataset.py ran no licence file found · pointer only · c8b1ea2dbf064b81 · report fixture: signature data:str/0/str, batch_size:int/0/int · returned tuple · level recorded 2026-09-24
marginal_prob_std in 5 papers utils.py ran no licence file found · pointer only · 057c095634d04249 · report fixture: signature t:float/0/float, device:str/0/str, beta_1:float/0/float, beta_0:float/0/float · returned tuple · level recorded 2026-09-24
mlp in 108 papers model.py ran · our draft was wrong no licence file found · pointer only · d466e7f1c4364a0b · report fixture: signature dims:list/1/int, activation:callable/0/?, output_activation:callable/0/? · returned Sequential · level recorded 2026-09-22
model_wrapper in 37 papers dpm_solver_pytorch.py ran; the contract check could not run (RAISES) no licence file found · pointer only · c38c4cd486f7a766 · report fixture: signature model:callable/0/?, noise_schedule:SimpleNoiseSchedule/0/?, model_type:str/0/str, model_kwargs:dict/0/?, guidance_type:str/0/str, condition:Tensor/2/float, unconditional_condition:Tensor/2/float, guidance_scale:float/0/float, classifier_fn:callable/0/?, classifier_kwargs:dict/0/? · returned function · level recorded 2026-09-24
return_range dataset.py ran · honoured contract no licence file found · pointer only · 732209d369d824c0 · report fixture: signature dataset:dict/0/?, max_episode_steps:int/0/int · returned tuple · level recorded 2026-09-24
CEP_Critic BDiffusion.py unverified no licence file found · pointer only · 3a044b5fa091a33b · report
EDA_policy BDiffusion.py unverified no licence file found · pointer only · 8f226f7f0a3a49f9 · report
IQL_Critic BDiffusion.py unverified no licence file found · pointer only · b9ad37c17cb01b28 · report
update_target BDiffusion.py unverified no licence file found · pointer only · 5e582540e0a940ea · 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. 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.

1 assembly on this paper: 1 harvested, 0 generated.

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

  1. EDA_policy entry · level 0 · unverified · 8f226f7f0a3a49f9
  2. CEP_Critic helper · level 0 · unverified · 3a044b5fa091a33b
  3. IQL_Critic helper · level 0 · unverified · b9ad37c17cb01b28
  4. update_target helper · level 0 · unverified · 5e582540e0a940ea
  5. asymmetric_l2_loss helper · level 1 · ran · our draft was wrong · 579d77f78c03773e

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="2407.09024") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continuous ControlD4RLLanguage ModelingLanguage Modellingcontinuous-control

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNDiffusion

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