Papers › Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization

Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization

5 Feb 2023arXiv:2302.02299archive 2025-07-28

Zichuan Lin, Xiapeng Wu, Mingfei Sun, Deheng Ye, Qiang Fu, Wei Yang, Wei Liu

Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse. In this paper, we show that the use of importance sampling could introduce high variance in the objective estimate. Specifically, we show in a principled way that the variance of importance sampling estimate grows quadratically with importance ratios and the large ratios could consequently jeopardize the effectiveness of surrogate objective optimization. We then propose a technique called sample dropout to bound the estimation variance by dropping out samples when their ratio deviation is too high. We instantiate this sample dropout technique on representative policy optimization algorithms, including TRPO, PPO, and ESPO, and demonstrate that it consistently boosts the performance of those DRL algorithms on both continuous and discrete action controls, including MuJoCo, DMControl and Atari video games. Our code is open-sourced at https://github.com/LinZichuan/sdpo.git.

PaperPDFCodeCode Syntology ran

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 12 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 6 ran (4 with no instrument failure; 2 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.

linzichuan/sdpo officialmentioned in papertfMITSyntology: 12 samples, 6 ran (2 instrument-failed) · 6 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

12 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 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
2ran · our draft was wrong
3ran
6unverified

Licence: 12 of the 12 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 linzichuan/sdpo. “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.

linzichuan/sdpo official repository 12 samples, 6 ran (2 instrument-failed) · 6 unverified
flat_concat in 7 papers baselines/ppo2/model.py ran · honoured contract MIT recorded; this copy not marked cleared · pointer only · f29202d8108bccd3 · report fixture: signature xs:list/1/EagerTensor · returned EagerTensor · level recorded 2026-09-24
make_output_format in 88 papers baselines/logger.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · bcd8b4acab199405 · report fixture: signature format:str/0/str, ev_dir:str/0/str, log_suffix:str/0/str · returned HumanOutputFormat · level recorded 2026-09-24
register in 66 papers baselines/common/models.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · a44574392d168384 · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-22
rolling_window in 16 papers baselines/results_plotter.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 895ca4b776fb6d6d · report fixture: signature a:ndarray/2/float, window:int/0/int · returned ndarray · level recorded 2026-09-25
ts2xy_monitor baselines/results_plotter.py ran MIT recorded; this copy not marked cleared · pointer only · 170bf6ea6525be34 · report fixture: signature ts:MockTimestampData/0/?, xaxis:str/0/str, yaxis:str/0/str · returned tuple · level recorded 2026-09-25
window_func in 14 papers baselines/results_plotter.py ran MIT recorded; this copy not marked cleared · pointer only · 43741b9339bd80da · report fixture: signature x:ndarray/1/float, y:ndarray/1/float, window:int/0/int, func:callable/0/? · returned tuple · level recorded 2026-09-25
build_impala_cnn baselines/common/models.py unverified MIT recorded; this copy not marked cleared · pointer only · 2bf5c781f8e4aad5 · report
cat_entropy in 7 papers baselines/a2c/utils.py unverified MIT recorded; this copy not marked cleared · pointer only · a3b4038f4e9b9479 · report
cat_entropy_softmax in 7 papers baselines/a2c/utils.py unverified MIT recorded; this copy not marked cleared · pointer only · 7082b4bbc0d9384f · report
profile in 89 papers baselines/logger.py unverified MIT recorded; this copy not marked cleared · pointer only · 91a934c3d796a9d4 · report
read_json in 250 papers baselines/logger.py unverified MIT recorded; this copy not marked cleared · pointer only · 88ef5a17fc986d9a · report
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
baselines/a2c/utils.py unverified MIT recorded; this copy not marked cleared · pointer only · 178099b1f8fb2b9d · report

Tasks

Deep Reinforcement LearningMuJoCo

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DropoutEntropy RegularizationPPOTRPO

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