Papers › Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning

Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning

19 Feb 2022arXiv:2202.09667archive 2025-07-28

Nathan Kallus, Xiaojie Mao, Kaiwen Wang, Zhengyuan Zhou

Off-policy evaluation and learning (OPE/L) use offline observational data to make better decisions, which is crucial in applications where online experimentation is limited. However, depending entirely on logged data, OPE/L is sensitive to environment distribution shifts -- discrepancies between the data-generating environment and that where policies are deployed. proposed distributionally robust OPE/L (DROPE/L) to address this, but the proposal relies on inverse-propensity weighting, whose estimation error and regret will deteriorate if propensities are nonparametrically estimated and whose variance is suboptimal even if not. For standard, non-robust, OPE/L, this is solved by doubly robust (DR) methods, but they do not naturally extend to the more complex DROPE/L, which involves a worst-case expectation. In this paper, we propose the first DR algorithms for DROPE/L with KL-divergence uncertainty sets. For evaluation, we propose Localized Doubly Robust DROPE (LDR²OPE) and show that it achieves semiparametric efficiency under weak product rates conditions. Thanks to a localization technique, LDR²OPE only requires fitting a small number of regressions, just like DR methods for standard OPE. For learning, we propose Continuum Doubly Robust DROPL (CDR²OPL) and show that, under a product rate condition involving a continuum of regressions, it enjoys a fast regret rate of 𝒪(N^(-1/2)) even when unknown propensities are nonparametrically estimated. We empirically validate our algorithms in simulations and further extend our results to general f-divergence uncertainty sets.

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 5 code samples harvested from 1 repository linked to this paper: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 4 ran (3 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

causalml/doubly-robust-dropel officialmentioned in papermentioned on GitHubjaxSyntology: 5 samples, 4 ran (1 instrument-failed) · 1 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

5 samples harvested: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 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.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
1ran
1unverified

Licence: 0 of the 5 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 causalml/doubly-robust-dropel. “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.

causalml/doubly-robust-dropel official repository 5 samples, 4 ran (1 instrument-failed) · 1 unverified
DataInput drorl/dro.py ran MIT (permissive) · 8440a2bb018f395b · report fixture: returned DataInput · level recorded 2026-09-22
_get_DR_reward_terms drorl/dro.py ran · honoured contract fingerprinted MIT (permissive) · 2676439a06c71fac · report fixture: signature W_n:float/0/float, dW_n:float/0/float, d2W_n:float/0/float, alpha:float/0/float, delta:float/0/float · returned tuple · level recorded 2026-09-22
_get_W_terms drorl/dro.py ran · violated contract fingerprinted MIT (permissive) · bd9a1d35cf0da051 · report fixture: signature r:ndarray/2/float, alpha:float/0/float, ipw:ndarray/2/float · returned tuple · level recorded 2026-09-22
ips drorl/dro.py ran · our draft was wrong MIT (permissive) · c7b056c2041e0dfb · report fixture: signature alpha:float/0/float, data:DataInput/0/?, delta:float/0/float · returned dict · level recorded 2026-09-22
ldml drorl/dro.py unverified MIT (permissive) · f9b41df03c3c58c9 · 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 Localized Doubly Robust DROPE (LDR 2 OPE) (graph method: Localized Doubly Robust DROPE (LDR 2 OPE)). 5 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. ldml entry · level 0 · unverified · f9b41df03c3c58c9
  2. DataInput helper · level 1 · ran · 8440a2bb018f395b
  3. ips helper · level 1 · ran · our draft was wrong · c7b056c2041e0dfb
  4. _get_DR_reward_terms loss · level 1 · ran · honoured contract · 2676439a06c71fac
  5. _get_W_terms loss · level 1 · ran · violated contract · bd9a1d35cf0da051

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="2202.09667") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Off-policy evaluation

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