Papers › Distance Weighted Supervised Learning for Offline Interaction Data
Distance Weighted Supervised Learning for Offline Interaction Data
Joey Hejna, Jensen Gao, Dorsa Sadigh
Sequential decision making algorithms often struggle to leverage different sources of unstructured offline interaction data. Imitation learning (IL) methods based on supervised learning are robust, but require optimal demonstrations, which are hard to collect. Offline goal-conditioned reinforcement learning (RL) algorithms promise to learn from sub-optimal data, but face optimization challenges especially with high-dimensional data. To bridge the gap between IL and RL, we introduce Distance Weighted Supervised Learning or DWSL, a supervised method for learning goal-conditioned policies from offline data. DWSL models the entire distribution of time-steps between states in offline data with only supervised learning, and uses this distribution to approximate shortest path distances. To extract a policy, we weight actions by their reduction in distance estimates. Theoretically, DWSL converges to an optimal policy constrained to the data distribution, an attractive property for offline learning, without any bootstrapping. Across all datasets we test, DWSL empirically maintains behavior cloning as a lower bound while still exhibiting policy improvement. In high-dimensional image domains, DWSL surpasses the performance of both prior goal-conditioned IL and RL algorithms. Visualizations and code can be found at https://sites.google.com/view/dwsl/home .
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 Distance Weighted Supervised Learning (DWSL), generated from the paper text (not the authors' code), at level 2 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)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Distance Weighted Supervised Learning (DWSL)') (how to connect); the free check have('2304.13774') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2304.13774")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2304.13774", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2304.13774")
Code
Syntology 27 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 8 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: community (archive-listed): 27 samples from 1 repository, 14 ran (4 with no instrument failure; 10 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.
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
27 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 13 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.
Licence: 0 of the 27 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 jhejna/dwsl. “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.
b091d78e039a3988 · report
fixture: signature batch:Tensor/2/float · returned Tensor · level recorded 2026-09-24 1120c18dc5d68b27 · report
fixture: signature low:dict/0/?, high:dict/0/?, shape:dict/0/?, dtype:dict/0/? · returned Dict · level recorded 2026-09-22 637f84c3975402d4 · report
fixture: signature batch:dict/0/? · returned bool · level recorded 2026-09-22 0954fb2e0809ee19 · report
fixture: signature d:dict/0/?, separator:str/0/str · returned dict · level recorded 2026-09-22 2560be95562059c8 · report
fixture: signature buffer:ndarray/2/float · returned int · level recorded 2026-09-22 4e1e3b9c7d834b3c · report
fixture: signature batch:dict/0/?, start:int/0/int, end:int/0/int · returned dict · level recorded 2026-09-22 253bd1783fdde661 · report
fixture: signature d:dict/0/?, separator:str/0/str · returned dict · level recorded 2026-09-22 b24b0464408ffe6f · report
fixture: signature space:Box/2/float · returned int64 · level recorded 2026-09-22 6a5e94d838f59eb4 · report
fixture: signature space:Box/2/float, capacity:int/0/int, begin_pad:tuple/1/int, end_pad:tuple/1/int · returned ndarray · level recorded 2026-09-22 a22c277630c0ae43 · report
fixture: signature space:Box/2/float · returned Box · level recorded 2026-09-22 743f3e742b59e566 · report
fixture: signature batch:dict/0/?, device:device/0/? · returned dict · 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 research/algs/dwsl.py ran; the contract check could not run (RAISES) MIT (permissive) ·
42e782a8ed834a53 · report
fixture: signature batch:Tensor/2/float · returned ndarray · level recorded 2026-09-22 census: 8 implementations from 8 papers, 3 distinct outputs across 3 buckets, one shared input per bucket research/algs/dwsl.py ran · our draft was wrong MIT (permissive) ·
95d8a0e297dabc98 · report
fixture: signature batch:dict/0/? · returned dict · level recorded 2026-09-22 f0ae192e0609afeb · report
fixture: signature batch:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22 0bc5a55290b00b3d · report
377a3792bec4c050 · report
28abd9986e85184e · report
2906ca8520e2b085 · 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 Distance Weighted Supervised Learning (DWSL) (graph method: Distance Weighted Supervised Learning (DWSL)), 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 2).
label matches by construction: the code was generated for this method (not judged by a model)
- compute_distance_estimate entry · level 2 · ran · honoured contract ·
fda4a8d8a4e6ed7a183ed91277cb2ad7a5e1a32618da9b03e1a7ed8ab4501b75
harvested Assembly for Distance Weighted Supervised Learning (DWSL) (graph method: Distance Weighted Supervised Learning (DWSL)). 27 bricks; individually on a fixture: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified. The assembly has not been run end-to-end.
- DWSL entry · level 0 · unverified ·
2849ec76164663e1 - OffPolicyAlgorithm helper · level 0 · unverified ·
44dba07f7e9beef9 - Algorithm helper · level 0 · unverified ·
0bc5a55290b00b3d - Empty helper · level 0 · unverified ·
61e694e983824ce6 - ReplayBuffer helper · level 0 · unverified ·
377a3792bec4c050 - IdentityProcessor helper · level 1 · ran ·
b091d78e039a3988 - Processor helper · level 0 · unverified ·
deee25387cd3a9ad - contains_tensors helper · level 1 · ran · violated contract ·
637f84c3975402d4 - get_from_batch helper · level 1 · ran · our draft was wrong ·
4e1e3b9c7d834b3c - to_device helper · level 1 · ran · our draft was wrong ·
743f3e742b59e566 - to_np helper · level 1 · ran; the contract check could not run (RAISES) ·
42e782a8ed834a53 - to_tensor helper · level 1 · ran · our draft was wrong ·
95d8a0e297dabc98 - unsqueeze helper · level 1 · ran · our draft was wrong ·
f0ae192e0609afeb - _get_space helper · level 1 · ran · our draft was wrong ·
1120c18dc5d68b27 - add_dummy_transition helper · level 0 · unverified ·
85f672bba25c666b - add_to_ep helper · level 0 · unverified ·
19868d3ab5b76af1 - concatenate helper · level 0 · unverified ·
28abd9986e85184e - get_buffer_bytes helper · level 1 · ran · honoured contract ·
2560be95562059c8 - load_data helper · level 0 · unverified ·
2906ca8520e2b085 - np_bytes_per_instance helper · level 1 · ran · honoured contract ·
b24b0464408ffe6f - np_dataset_alloc helper · level 1 · ran; the contract check could not run (RAISES) ·
6a5e94d838f59eb4 - remove_stack_dim helper · level 1 · ran · our draft was wrong ·
a22c277630c0ae43 - save_data helper · level 0 · unverified ·
135a3fcc0598994a - set_in_batch helper · level 0 · unverified ·
7830c871b6faa561 - nest_dict helper · level 1 · ran · our draft was wrong ·
253bd1783fdde661 - flatten_dict helper · level 1 · ran · our draft was wrong ·
0954fb2e0809ee19 - _flatten_dict_helper helper · level 0 · unverified ·
1a771a68f2829a00
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="2304.13774") 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.
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