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 ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.07226")

Code

Syntology Ran 20 of 29 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 2 ran · honoured contract; 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 13 ran with no contract checked.

By repository: official repository: 29 samples from 1 repository, 20 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

rlatjddbs/ssd officialmentioned in paperpytorch 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; 2 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
1ran · fixture could not drive it
13ran
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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

Conv1dBlock rlatjddbs/SSD/dc/dc.py official repository ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7d5fe12da38ea3f5 · report
Downsample1d rlatjddbs/SSD/dc/dc.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · 52a4fe52c83d4acb · report
HindsightCritic rlatjddbs/SSD/dc/dc.py official repository ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · d5a64382ebf227b3 · report
ResidualTemporalBlock rlatjddbs/SSD/dc/dc.py official repository ran no licence file found · pointer only · d7aa55fb04049d51 · report
Timer rlatjddbs/SSD/dc/dc.py official repository ran · metamorphic tier: well formed fingerprinted no licence file found · pointer only · 92d5319d3f565de2 · report
Upsample1d rlatjddbs/SSD/dc/dc.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · 3ff139e92610787b · report
WeightedL1 rlatjddbs/SSD/dc/dc.py official repository ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · dfe036fdc5d15991 · report
WeightedL2 rlatjddbs/SSD/dc/dc.py official repository ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 264959cf75b98c11 · report
batch_to_device rlatjddbs/SSD/dc/dc.py official repository ran · our draft was wrong no licence file found · pointer only · 61a25fc7fbbca3a7 · report
cycle rlatjddbs/SSD/dc/dc.py official repository ran · our draft was wrong no licence file found · pointer only · 33fe2742a5ad304c · report
discounted_return rlatjddbs/SSD/dc/dc.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 1aec056948f8cf9f · report
discounted_return rlatjddbs/ssd/bc/agents.py official repository ran no licence file found · pointer only · 09e5d94abb73ef7b · report
goal_distance rlatjddbs/ssd/bc/base_agent.py official repository ran fingerprinted no licence file found · pointer only · 6eb59c36d3f33fe4 · report
increasing_schedule rlatjddbs/ssd/utils/eval_module.py official repository ran no licence file found · pointer only · 67c16af0a0af4b08 · report
main rlatjddbs/SSD/dc/dc.py official repository ran no licence file found · pointer only · 77cff4b5b63e486e · report
main_maze rlatjddbs/ssd/utils/eval_module.py official repository ran no licence file found · pointer only · b33aeaa0860fa787 · report
pad_horizon rlatjddbs/SSD/dc/dc.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 4afff382ab811901 · report
to_device rlatjddbs/SSD/dc/dc.py official repository ran · our draft was wrong no licence file found · pointer only · 06e523fad286371d · report
to_np rlatjddbs/SSD/dc/dc.py official repository ran · honoured contract no licence file found · pointer only · 0e8d8251e66ab160 · report
to_torch rlatjddbs/SSD/dc/dc.py official repository ran · our draft was wrong no licence file found · pointer only · a31d5ee8d54d737b · report
DiffuserCritic rlatjddbs/SSD/dc/dc.py official repository unverified no licence file found · pointer only · 0b6de38ffcf51a1e · report
GaussianDiffusion rlatjddbs/SSD/dc/dc.py official repository unverified no licence file found · pointer only · 880a368bc0c23611 · report
TemporalUnetTransformer rlatjddbs/SSD/dc/dc.py official repository unverified no licence file found · pointer only · 0d1e4f14a279e96a · report
ValueL1 rlatjddbs/SSD/dc/dc.py official repository unverified no licence file found · pointer only · ddcd47f61ee383c7 · report
ValueL2 rlatjddbs/SSD/dc/dc.py official repository unverified no licence file found · pointer only · 14519433f6d88b11 · report
ValueLoss rlatjddbs/SSD/dc/dc.py official repository unverified no licence file found · pointer only · ab29d5d735d5a9cb · report
WeightedLoss rlatjddbs/SSD/dc/dc.py official repository unverified no licence file found · pointer only · aa6bfea7b5d980c8 · report
copy_nn_module rlatjddbs/SSD/dc/dc.py official repository unverified no licence file found · pointer only · 26a7c332d2d6fdbb · report
soft_copy_nn_module rlatjddbs/SSD/dc/dc.py official repository unverified no licence file found · pointer only · 49af4ec227a55bc8 · report

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