Papers › Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task...
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
Haoran He, Chenjia Bai, Kang Xu, Zhuoran Yang, Weinan Zhang, Dong Wang, Bin Zhao, Xuelong Li
Diffusion models have demonstrated highly-expressive generative capabilities in vision and NLP. Recent studies in reinforcement learning (RL) have shown that diffusion models are also powerful in modeling complex policies or trajectories in offline datasets. However, these works have been limited to single-task settings where a generalist agent capable of addressing multi-task predicaments is absent. In this paper, we aim to investigate the effectiveness of a single diffusion model in modeling large-scale multi-task offline data, which can be challenging due to diverse and multimodal data distribution. Specifically, we propose Multi-Task Diffusion Model (MTDiff), a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis in multi-task offline settings. MTDiff leverages vast amounts of knowledge available in multi-task data and performs implicit knowledge sharing among tasks. For generative planning, we find MTDiff outperforms state-of-the-art algorithms across 50 tasks on Meta-World and 8 maps on Maze2D. For data synthesis, MTDiff generates high-quality data for testing tasks given a single demonstration as a prompt, which enhances the low-quality datasets for even unseen tasks.
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 Multi-Task Diffusion Model (MTDIFF), 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). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Multi-Task Diffusion Model (MTDIFF)') (how to connect); the free check have('2305.18459') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2305.18459")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2305.18459", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2305.18459")
Code
Syntology 30 code samples harvested from 2 repositories linked to this paper: 19 ran (of which 3 constructed an object rather than computing a result; 14 with no instrument failure: 8 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 22 samples from 1 repository, 15 ran (10 with no instrument failure; 5 where Syntology's instrument failed); found in paper text by Syntology: 8 samples from 1 repository, 4 ran (4 with no instrument failure; 0 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 3 of its repositories that Syntology harvested for other papers:
- tinkoff-ai/CORL, found in paper text by Syntology: Syntology's graph links these samples to CORL: Research-oriented Deep Offline Reinforcement Learning Library (arXiv:2210.07105; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), Synthetic Experience Replay (arXiv:2303.06614; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), Cross-Domain Policy Adaptation by Capturing Representation Mismatch (arXiv:2405.15369; that paper's own run record: 10 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.
- kzl/decision-transformer, found in paper text by Syntology: Syntology's graph links these samples to Online Decision Transformer (arXiv:2202.05607; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.
- Farama-Foundation/D4RL, found in paper text by Syntology: Syntology's graph links these samples to D4RL: Datasets for Deep Data-Driven Reinforcement Learning (arXiv:2004.07219; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method.
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.
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
30 samples harvested: 19 ran (of which 3 constructed an object rather than computing a result; 14 with no instrument failure: 8 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 11 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.
Licence: 4 of the 30 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 2 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.
5347209028588046 · report
fixture: signature env:MockEnv/0/? · returned function · level recorded 2026-09-25 785632d29b87adad · report
fixture: signature x:ndarray/1/int · returned ndarray · level recorded 2026-09-25 3ca83b3e96824f00 · report
fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-25 b6113e0f43155a33 · report
fixture: signature timesteps:int/0/int, s:float/0/float, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22 8d04d499d75080d0 · report
fixture: signature model:callable/0/?, x:Tensor/2/float, cond:Tensor/2/float, task:Tensor/2/float, value:Tensor/2/float, context_mask:Tensor/2/float, t:Tensor/1/int, sample_kwargs:dict/0/? · returned tuple · level recorded 2026-09-22 2fd70118265255f8 · report
fixture: signature sample:ndarray/1/float · returned tuple · level recorded 2026-09-25 census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket diffuser/datasets/normalization.py ran · our draft was wrong MIT (permissive) ·
505d6b06c543b4fb · report
fixture: signature dataset:dict/0/?, path_lengths:list/1/int · returned dict · level recorded 2026-09-25 5321d9d86ff019c1 · report
fixture: signature trajectories:list/1/dict, num_episodes:int/0/int, num_steps:int/0/int, is_meta:bool/0/bool, is_maze:bool/0/bool · returned ndarray · level recorded 2026-09-26 6c4cc9bc7e5e5859 · report
fixture: signature prompt_trajectories:list/1/list, cond:Tensor/1/int, num_episodes:int/0/int, num_steps:int/0/int, is_meta:bool/0/bool · returned Tensor · level recorded 2026-09-26 69e493e37778664c · report
fixture: signature name:MockEnvironment/0/? · returned MockEnvironment · level recorded 2026-09-24 80cbf0ec77b1d134 · report
fixture: signature maze_str:str/0/str · returned ndarray · level recorded 2026-09-26 c409be426eec3eec · report
fixture: signature x:Tensor/2/float, values:Tensor/1/float · returned tuple · level recorded 2026-09-22 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 diffuser/utils/arrays.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only ·
0e8d8251e66ab160 · report
fixture: signature x:Tensor/2/float · returned ndarray · level recorded 2026-09-22 census: 5 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket diffuser/utils/arrays.py ran · our draft was wrong MIT (permissive) ·
134173215340e0d1 · report
fixture: signature x:dict/0/?, dtype:dtype/0/?, device:str/0/str · returned dict · level recorded 2026-09-24 47c7ce0ace6e7c47 · report
fixture: signature timesteps:int/0/int, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22 census: 9 implementations from 12 papers, 4 distinct outputs across 3 buckets, one shared input per bucket diffuser/models/helpers.py unverified MIT (permissive) ·
09c8479d9a5b3e06 · report
6b688f0cd038f65e · report
65e5c27060559602 · report
54442074c20e0e8f · report
27c640b42f4e6a73 · report
bb6694e97ebbdbb5 · report
00a33466c69c5705 · report
bb0b654d7e2f043a · report
fixture: returned WeightedL1 · level recorded 2026-09-22 63bb8b129db38dfb · report
fixture: returned WeightedL2 · level recorded 2026-09-22 31a6a65466c90f16 · report
fixture: returned WeightedLoss · level recorded 2026-09-22 51db163798eb0f5e · report
fixture: signature batch_size:int/0/int, i:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-22 b647fa958c28b7a0 · 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". 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 Multi-Task Diffusion Model (MTDIFF) (graph method: Multi-Task Diffusion Model (MTDIFF)), 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 is recorded, but its report lists no property test that passed on both.
label matches by construction: the code was generated for this method (not judged by a model)
- classifier_free_guidance_noise_prediction entry · level 3 · ran · honoured contract ·
8b58000ebc536bfe8b4c5ed9d09d7a89cc7b39c385394fd40feaea3969de4153
harvested Assembly for Multi-Task Diffusion Model (MTDIFF) (graph method: Multi-Task Diffusion Model (MTDIFF)). 13 bricks; individually on a fixture: 8 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
- GaussianDiffusion entry · level 0 · unverified ·
b647fa958c28b7a0 - apply_conditioning data_transform · level 1 · ran · our draft was wrong ·
b3d593fb33f79ac5 - cosine_beta_schedule helper · level 1 · ran · honoured contract ·
b6113e0f43155a33 - default_sample_fn sampler · level 1 · ran · our draft was wrong ·
896418fd494c4d3d - extract helper · level 0 · unverified ·
09c8479d9a5b3e06 - make_timesteps scheduler · level 1 · ran · honoured contract ·
51db163798eb0f5e - sort_by_values helper · level 1 · ran · honoured contract ·
c409be426eec3eec - ValueLoss helper · level 0 · unverified ·
2033d022f4c21dd8 - WeightedLoss loss · level 1 · ran ·
31a6a65466c90f16 - ValueL1 helper · level 0 · unverified ·
15f5f25cbe9d72e0 - ValueL2 helper · level 0 · unverified ·
4b9ad2741a65b9b0 - WeightedL1 helper · level 1 · ran ·
bb0b654d7e2f043a - WeightedL2 helper · level 1 · ran ·
63bb8b129db38dfb
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="2305.18459") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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