Papers › Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL

Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL

11 Feb 2024arXiv:2402.07226archive 2025-07-28

Sungyoon Kim, Yunseon Choi, Daiki E. Matsunaga, Kee-Eung Kim

Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected behavior datasets. In this setting, the reward feedback is typically absent except when the goal is achieved, which makes it difficult to learn policies especially from a finite dataset of suboptimal behaviors. In addition, realistic scenarios involve long-horizon planning, which necessitates the extraction of useful skills within sub-trajectories. Recently, the conditional diffusion model has been shown to be a promising approach to generate high-quality long-horizon plans for RL. However, their practicality for the goal-conditioned setting is still limited due to a number of technical assumptions made by the methods. In this paper, we propose SSD (Sub-trajectory Stitching with Diffusion), a model-based offline GCRL method that leverages the conditional diffusion model to address these limitations. In summary, we use the diffusion model that generates future plans conditioned on the target goal and value, with the target value estimated from the goal-relabeled offline dataset. We report state-of-the-art performance in the standard benchmark set of GCRL tasks, and demonstrate the capability to successfully stitch the segments of suboptimal trajectories in the offline data to generate high-quality plans.

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 29 code samples harvested from 1 repository linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 29 samples from 1 repository, 20 ran (14 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

rlatjddbs/ssd officialmentioned in paperpytorchSyntology: 29 samples, 20 ran (6 instrument-failed) · 9 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

29 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 6 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 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
1ran · violated contract
4ran · our draft was wrong
2ran; the contract check could not run
11ran
9unverified

Licence: 29 of the 29 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 rlatjddbs/ssd. “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.

rlatjddbs/ssd official repository 29 samples, 20 ran (6 instrument-failed) · 9 unverified
Conv1dBlock dc/dc.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7d5fe12da38ea3f5 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
Downsample1d in 5 papers dc/dc.py ran · metamorphic tier: invariant no licence file found · pointer only · 52a4fe52c83d4acb · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
HindsightCritic dc/dc.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · d5a64382ebf227b3 · report fixture: signature state:Tensor/2/float, action:Tensor/2/float, goal:Tensor/2/float · returned tuple · level recorded 2026-09-22
ResidualTemporalBlock dc/dc.py ran no licence file found · pointer only · d7aa55fb04049d51 · report fixture: signature x:Tensor/3/float, t:Tensor/2/float · returned Tensor · level recorded 2026-09-24
Timer in 12 papers dc/dc.py ran · metamorphic tier: well formed no licence file found · pointer only · 92d5319d3f565de2 · report fixture: signature reset:bool/0/bool · returned float · level recorded 2026-09-22
Upsample1d in 6 papers dc/dc.py ran · metamorphic tier: invariant no licence file found · pointer only · 3ff139e92610787b · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
WeightedL1 in 8 papers dc/dc.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · dfe036fdc5d15991 · report fixture: signature pred:Tensor/3/float, targ:Tensor/3/float · returned Tensor · level recorded 2026-09-22
WeightedL2 in 8 papers dc/dc.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 264959cf75b98c11 · report fixture: signature pred:Tensor/3/float, targ:Tensor/3/float · returned Tensor · level recorded 2026-09-22
batch_to_device in 18 papers dc/dc.py ran · our draft was wrong no licence file found · pointer only · 61a25fc7fbbca3a7 · report fixture: signature batch:TestBatch/1/Tensor, device:str/0/str · returned TestBatch · level recorded 2026-09-22
cycle dc/dc.py ran · our draft was wrong no licence file found · pointer only · 33fe2742a5ad304c · report fixture: signature dl:list/1/tuple · returned generator · level recorded 2026-09-22
discounted_return dc/dc.py ran · honoured contract fingerprinted no licence file found · pointer only · 1aec056948f8cf9f · report fixture: signature rewards:ndarray/1/float, gamma:float/0/float, reward_offset:bool/0/bool · returned tuple · level recorded 2026-09-22
discounted_return bc/agents.py ran no licence file found · pointer only · 09e5d94abb73ef7b · report fixture: signature rewards:ndarray/2/float, gamma:float/0/float, reward_offset:bool/0/bool · returned tuple · level recorded 2026-09-24
goal_distance in 7 papers bc/base_agent.py ran · violated contract fingerprinted no licence file found · pointer only · 6eb59c36d3f33fe4 · report fixture: signature goal_a:ndarray/2/float, goal_b:ndarray/2/float · returned ndarray · level recorded 2026-09-24
increasing_schedule utils/eval_module.py ran no licence file found · pointer only · 67c16af0a0af4b08 · report fixture: signature t:int/0/int, gamma:float/0/float, horizon:int/0/int, max_epi_len:int/0/int · returned float · level recorded 2026-09-24
main in 235 papers dc/dc.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 77cff4b5b63e486e · report fixture: signature env:MockEnv/0/?, n_episodes:int/0/int, policy:callable/0/?, target_v:float/0/float · returned tuple · level recorded 2026-09-22
main_maze utils/eval_module.py ran no licence file found · pointer only · b33aeaa0860fa787 · report fixture: signature env:MazeEnv/0/?, n_episodes:int/0/int, policy:MinimalPolicy/0/?, target_v:float/0/float · returned tuple · level recorded 2026-09-24
pad_horizon dc/dc.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 4afff382ab811901 · report fixture: signature x:Tensor/3/float, horizon:int/0/int · returned Tensor · level recorded 2026-09-22
to_device in 75 papers dc/dc.py ran · our draft was wrong no licence file found · pointer only · 06e523fad286371d · report fixture: signature x:dict/0/?, device:str/0/str · returned dict · 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
dc/dc.py ran · honoured contract no licence file found · pointer only · 0e8d8251e66ab160 · report fixture: signature x:Tensor/2/float · returned ndarray · level recorded 2026-09-22
to_torch in 53 papers
census: 5 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
dc/dc.py ran · our draft was wrong no licence file found · pointer only · a31d5ee8d54d737b · report fixture: signature x:dict/0/?, dtype:dtype/0/?, device:str/0/str · returned dict · level recorded 2026-09-22
DiffuserCritic dc/dc.py unverified no licence file found · pointer only · 0b6de38ffcf51a1e · report
GaussianDiffusion in 61 papers dc/dc.py unverified no licence file found · pointer only · 880a368bc0c23611 · report
TemporalUnetTransformer dc/dc.py unverified no licence file found · pointer only · 0d1e4f14a279e96a · report
ValueL1 dc/dc.py unverified no licence file found · pointer only · ddcd47f61ee383c7 · report
ValueL2 dc/dc.py unverified no licence file found · pointer only · 14519433f6d88b11 · report
ValueLoss dc/dc.py unverified no licence file found · pointer only · ab29d5d735d5a9cb · report
WeightedLoss in 7 papers dc/dc.py unverified no licence file found · pointer only · aa6bfea7b5d980c8 · report
copy_nn_module dc/dc.py unverified no licence file found · pointer only · 26a7c332d2d6fdbb · report
soft_copy_nn_module dc/dc.py unverified no licence file found · pointer only · 49af4ec227a55bc8 · 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 SSD (Subtrajectory Stitching with Diffusion) (graph method: SSD (Subtrajectory Stitching with Diffusion)). 31 bricks; individually on a fixture: 21 ran (of which 1 constructed an object rather than computing a result; 15 with no instrument failure: 5 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. DiffuserCritic entry · level 0 · unverified · 0b6de38ffcf51a1e
  2. EMA helper · level 1 · ran · cb039993bd16f94c
  3. GaussianDiffusion model · level 0 · unverified · 880a368bc0c23611
  4. HindsightCritic helper · level 1 · ran · d5a64382ebf227b3
  5. TemporalUnetTransformer helper · level 0 · unverified · 0d1e4f14a279e96a
  6. Timer helper · level 1 · ran · 92d5319d3f565de2
  7. batch_to_device helper · level 1 · ran · our draft was wrong · 61a25fc7fbbca3a7
  8. copy_nn_module helper · level 0 · unverified · 26a7c332d2d6fdbb
  9. cycle helper · level 1 · ran · our draft was wrong · 33fe2742a5ad304c
  10. main helper · level 1 · ran; the contract check could not run (RAISES) · 77cff4b5b63e486e
  11. pad_horizon data_transform · level 1 · ran; the contract check could not run (RAISES) · 4afff382ab811901
  12. cosine_beta_schedule helper · level 1 · ran · honoured contract · b6113e0f43155a33
  13. extract helper · level 0 · unverified · 09c8479d9a5b3e06
  14. linear_beta_schedule helper · level 1 · ran · honoured contract · 63d21c7afce1a9e5
  15. vp_beta_schedule helper · level 1 · ran · honoured contract · 47c7ce0ace6e7c47
  16. soft_copy_nn_module helper · level 0 · unverified · 49af4ec227a55bc8
  17. to_np helper · level 1 · ran · honoured contract · 0e8d8251e66ab160
  18. to_torch helper · level 1 · ran · our draft was wrong · a31d5ee8d54d737b
  19. Conv1dBlock helper · level 1 · ran · 7d5fe12da38ea3f5
  20. Downsample1d helper · level 1 · ran · 52a4fe52c83d4acb
  21. ResidualTemporalBlock helper · level 1 · ran · d7aa55fb04049d51
  22. SinusoidalPosEmb helper · level 1 · ran · 0bd2edd74d66fbd9
  23. Upsample1d helper · level 1 · ran · 3ff139e92610787b
  24. to_device helper · level 1 · ran · our draft was wrong · 06e523fad286371d
  25. discounted_return helper · level 1 · ran · honoured contract · 1aec056948f8cf9f
  26. ValueLoss helper · level 0 · unverified · ab29d5d735d5a9cb
  27. WeightedLoss helper · level 0 · unverified · aa6bfea7b5d980c8
  28. ValueL1 helper · level 0 · unverified · ddcd47f61ee383c7
  29. ValueL2 helper · level 0 · unverified · 14519433f6d88b11
  30. WeightedL1 helper · level 1 · ran · dfe036fdc5d15991
  31. WeightedL2 helper · level 1 · ran · 264959cf75b98c11

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="2402.07226") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Offline RL

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionConvolutionDiffusionNon Maximum SuppressionSETSSD

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