Papers › Offline Behavior Distillation

Offline Behavior Distillation

30 Oct 2024arXiv:2410.22728archive 2025-07-28

Shiye Lei, Sen Zhang, DaCheng Tao

Massive reinforcement learning (RL) data are typically collected to train policies offline without the need for interactions, but the large data volume can cause training inefficiencies. To tackle this issue, we formulate offline behavior distillation (OBD), which synthesizes limited expert behavioral data from sub-optimal RL data, enabling rapid policy learning. We propose two naive OBD objectives, DBC and PBC, which measure distillation performance via the decision difference between policies trained on distilled data and either offline data or a near-expert policy. Due to intractable bi-level optimization, the OBD objective is difficult to minimize to small values, which deteriorates PBC by its distillation performance guarantee with quadratic discount complexity 𝒪(1/(1-γ)²). We theoretically establish the equivalence between the policy performance and action-value weighted decision difference, and introduce action-value weighted PBC (Av-PBC) as a more effective OBD objective. By optimizing the weighted decision difference, Av-PBC achieves a superior distillation guarantee with linear discount complexity 𝒪(1/(1-γ)). Extensive experiments on multiple D4RL datasets reveal that Av-PBC offers significant improvements in OBD performance, fast distillation convergence speed, and robust cross-architecture/optimizer generalization.

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 16 code samples harvested from 1 repository linked to this paper: 9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 9 ran (6 with no instrument failure; 3 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 9 samples that ran have no recorded date.

leaveslei/obd officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 9 ran (3 instrument-failed) · 7 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

16 samples harvested: 9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
3ran · our draft was wrong
3ran
7unverified

Licence: 16 of the 16 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 leaveslei/obd. “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.

leaveslei/obd official repository 16 samples, 9 ran (3 instrument-failed) · 7 unverified
FullyConnectedQFunction data_lib/syndset.py ran no licence file found · pointer only · 2adcff124b835b01 · report fixture: returned FullyConnectedQFunction · level recorded 2026-09-22
_fanin_init data_lib/syndset.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 7b14e32ff9c72f54 · report fixture: signature tensor:Tensor/2/float, alpha:float/0/float · returned Tensor · level recorded 2026-09-22
dict2namespace in 31 papers obd_bptt.py ran · our draft was wrong no licence file found · pointer only · bd1f17e427bf51a5 · report fixture: signature config:dict/0/? · returned Namespace · level recorded, date not recorded
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
obd_bptt.py ran · honoured contract no licence file found · pointer only · 3155dcd1f7d26b1f · report fixture: signature data:list/1/Tensor · returned Tensor · level recorded, date not recorded
get_hms in 8 papers utils.py ran · honoured contract fingerprinted no licence file found · pointer only · bb104479d26e39c3 · report fixture: signature seconds:int/0/int · returned tuple · level recorded 2026-09-22
merge_args in 5 papers configs/command_parser.py ran · our draft was wrong no licence file found · pointer only · d35eb4a0d5666e7f · report fixture: signature args:Namespace/0/?, config:SimpleConfig/0/? · returned SimpleConfig · level recorded, date not recorded
merge_args in 5 papers configs/command_parser.py ran no licence file found · pointer only · dc43b3f4e178b8c1 · report fixture: signature args:Args/0/?, config:Config/0/? · returned Config · level recorded 2026-09-25
normalize_states in 15 papers utils.py ran · honoured contract fingerprinted no licence file found · pointer only · ba80f9ff81b1de5f · report fixture: signature states:ndarray/2/float, mean:ndarray/1/float, std:ndarray/1/float · returned ndarray · level recorded, date not recorded
wrap_env in 9 papers utils.py ran no licence file found · pointer only · 6f4380c7d15b6e42 · report fixture: signature env:TimeLimit/0/?, state_mean:float/0/float, state_std:float/0/float, reward_scale:float/0/float · returned TransformReward · level recorded 2026-09-25
Net in 54 papers data_lib/syndset.py unverified no licence file found · pointer only · c0927665fe7f7dc7 · report
_constant_bias_init data_lib/syndset.py unverified no licence file found · pointer only · d540ae0c1a5c67bc · report
_orthogonal_init data_lib/syndset.py unverified no licence file found · pointer only · 30ac7cd064d9ecda · report
get_data in 223 papers data_lib/dset.py unverified no licence file found · pointer only · defae8a6ac156ec3 · report
init_module_weights data_lib/syndset.py unverified no licence file found · pointer only · c481fbf6b3811329 · report
layer_init in 46 papers data_lib/syndset.py unverified no licence file found · pointer only · f297771ebb6401b8 · report
orthogonal_init in 12 papers data_lib/syndset.py unverified no licence file found · pointer only · 1ec0ea84d63a7360 · 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 Offline Behavior Distillation (OBD) (graph method: Offline Behavior Distillation (OBD)). 8 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. Net entry · level 0 · unverified · c0927665fe7f7dc7
  2. FullyConnectedQFunction helper · level 1 · ran · 2adcff124b835b01
  3. init_module_weights helper · level 0 · unverified · c481fbf6b3811329
  4. orthogonal_init helper · level 0 · unverified · 1ec0ea84d63a7360
  5. _constant_bias_init helper · level 0 · unverified · d540ae0c1a5c67bc
  6. _orthogonal_init helper · level 0 · unverified · 30ac7cd064d9ecda
  7. layer_init helper · level 0 · unverified · f297771ebb6401b8
  8. _fanin_init helper · level 1 · ran · our draft was wrong · 7b14e32ff9c72f54

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="2410.22728") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

D4RLReinforcement Learning (RL)

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