Papers › How to Leverage Diverse Demonstrations in Offline Imitation Learning

How to Leverage Diverse Demonstrations in Offline Imitation Learning

24 May 2024arXiv:2405.17476archive 2025-07-28

Sheng Yue, Jiani Liu, Xingyuan Hua, Ju Ren, Sen Lin, Junshan Zhang, Yaoxue Zhang

Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors from noisy data. In general, current approaches to the problem select data building on state-action similarity to given expert demonstrations, neglecting precious information in (potentially abundant) diverse state-actions that deviate from expert ones. In this paper, we introduce a simple yet effective data selection method that identifies positive behaviors based on their resultant states -- a more informative criterion enabling explicit utilization of dynamics information and effective extraction of both expert and beneficial diverse behaviors. Further, we devise a lightweight behavior cloning algorithm capable of leveraging the expert and selected data correctly. In the experiments, we evaluate our method on a suite of complex and high-dimensional offline IL benchmarks, including continuous-control and vision-based tasks. The results demonstrate that our method achieves state-of-the-art performance, outperforming existing methods on 20/21 benchmarks, typically by 2-5x, while maintaining a comparable runtime to Behavior Cloning (BC).

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

The archive's official repository (hansenhua/ilid-offline-imitation-learning) was not harvested; the 13 samples below come from 3 repositories the archive does not mark official.

Syntology 13 code samples harvested from 3 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 13 samples from 3 repositories, 8 ran (7 with no instrument failure; 1 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hansenhua/ilid-offline-imitation-learning officialmentioned in paperpytorchSyntology: not harvested 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

13 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 5 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
1ran · our draft was wrong
6ran
5unverified

Licence: 8 of the 13 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 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. “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.

ryanxhr/DWBC found in paper text by Syntology 4 samples, 1 ran (0 instrument-failed) · 3 unverified
qlearning_dataset get_dataset.py ran MIT (permissive) · 119b5a0ec83785b2 · report fixture: signature dataset:dict/0/?, terminate_on_end:bool/0/bool · returned dict · level recorded 2026-09-24
dataset_setting1 get_dataset.py unverified MIT (permissive) · c55b1773d8caec85 · report
dataset_setting2 get_dataset.py unverified MIT (permissive) · ef7685bff6390ccd · report
eval_policy in 15 papers main_setting_demodice.py unverified MIT (permissive) · 8205eb63bd6bd52d · report
tinkoff-ai/CORL found in paper text by Syntology 1 sample, 0 ran · 1 unverified
keep_best_trajectories algorithms/offline/any_percent_bc.py unverified Apache-2.0 (permissive) · da056a6fdaccaacf · report
liziniu/ISWBC found in paper text by Syntology 8 samples, 7 ran (1 instrument-failed) · 1 unverified
clamp in 78 papers
census: 7 implementations from 8 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
atari/experiments/agents/iswbc_agent.py ran no licence file found · pointer only · 3336fdca39b09846 · report fixture: signature x:SymbolicTensor/2/float, clip_min:float/0/float, clip_max:float/0/float · returned SymbolicTensor · level recorded 2026-09-24
concat_trajectories mujoco/dataset_utils.py ran · honoured contract no licence file found · pointer only · cc5f4add4c5cc2b4 · report fixture: signature trajectories:list/1/ndarray · returned ndarray · level recorded 2026-09-24
get_dataset in 285 papers mujoco/dataset_utils.py ran no licence file found · pointer only · f013924cbc909a48 · report fixture: signature dir_name:str/0/str, env_id:str/0/str, data_name:str/0/str · returned dict · level recorded 2026-09-24
get_replay_dataset mujoco/dataset_utils.py ran no licence file found · pointer only · ef7fbd2aab415a25 · report fixture: signature dir_name:str/0/str, env_id:str/0/str, data_name:str/0/str · returned dict · level recorded 2026-09-24
stable_scaled_log_softmax atari/experiments/agents/iswbc_agent.py ran no licence file found · pointer only · 8ceadd2844bebbfb · report fixture: signature x:SymbolicTensor/2/float, tau:float/0/float, axis:int/0/int · returned SymbolicTensor · level recorded 2026-09-24
stable_softmax in 7 papers atari/experiments/agents/iswbc_agent.py ran no licence file found · pointer only · 2de1ae4938d1cdca · report fixture: signature x:SymbolicTensor/2/float, tau:float/0/float, axis:int/0/int · returned SymbolicTensor · level recorded 2026-09-24
timeit in 59 papers atari/experiments/replay_memory.py ran · our draft was wrong no licence file found · pointer only · bde9000f5d0e5e03 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-24
evaluate in 514 papers mujoco/run_iswbc_full_replay.py unverified no licence file found · pointer only · 83e1823efe8292e6 · 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 data selection method (graph method: data selection method). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. keep_best_trajectories entry · level 0 · unverified · da056a6fdaccaacf

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="2405.17476") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continuous ControlImitation Learningcontinuous-control

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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