SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.02299 · 2023

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

arXiv · PDF · Open in the Atlas

Code that ran

6 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2302.02299.json · badge: /api/ran/2302.02299.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
linzichuan/sdpo canonical (classifier label)
classifier basis not recorded on the link
6 ran · 6 no recorded run
FunctionStatusWhere it lives
flat_concat Ran
ran, honoured the contract we drafted
linzichuan/sdpo/baselines/ppo2/model.py
pointer only (licence: MIT); the stored copy get_code serves, from milanganai/milanganai.github.io, is pointer only (licence: NONE) · get_code("f29202d8108bccd3")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_output_format Ran
ran; our contract draft was wrong, not the code
linzichuan/sdpo/baselines/logger.py
pointer only (licence: MIT) · get_code("bcd8b4acab199405")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

register Ran
ran; our contract draft was wrong, not the code
linzichuan/sdpo/baselines/common/models.py
pointer only (licence: MIT) · get_code("a44574392d168384")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rolling_window Ran
ran on a synthesized input
linzichuan/sdpo/baselines/results_plotter.py
pointer only (licence: MIT); the stored copy get_code serves, from knowledgetechnologyuhh/goal_conditioned_RL_baselines, is pointer only (licence: MIT) · get_code("895ca4b776fb6d6d")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ts2xy_monitor Ran
ran on a synthesized input
linzichuan/sdpo/baselines/results_plotter.py
pointer only (licence: MIT) · get_code("170bf6ea6525be34")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

window_func Ran
ran on a synthesized input
linzichuan/sdpo/baselines/results_plotter.py
pointer only (licence: MIT); the stored copy get_code serves, from knowledgetechnologyuhh/goal_conditioned_RL_baselines, is pointer only (licence: MIT) · get_code("43741b9339bd80da")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_impala_cnn Not yet run
unverified (harvested, no recorded run)
linzichuan/sdpo/baselines/common/models.py
pointer only (licence: MIT) · get_code("2bf5c781f8e4aad5")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

cat_entropy Not yet run
unverified (harvested, no recorded run)
linzichuan/sdpo/baselines/a2c/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuohanW/RED, is pointer only (licence: MIT) · get_code("a3b4038f4e9b9479")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

cat_entropy_softmax Not yet run
unverified (harvested, no recorded run)
linzichuan/sdpo/baselines/a2c/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuohanW/RED, is pointer only (licence: MIT) · get_code("7082b4bbc0d9384f")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

profile Not yet run
unverified (harvested, no recorded run)
linzichuan/sdpo/baselines/logger.py
pointer only (licence: MIT) · get_code("91a934c3d796a9d4")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

read_json Not yet run
unverified (harvested, no recorded run)
linzichuan/sdpo/baselines/logger.py
pointer only (licence: MIT) · get_code("88ef5a17fc986d9a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

sample Not yet run
unverified (harvested, no recorded run)
linzichuan/sdpo/baselines/a2c/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuohanW/RED, is pointer only (licence: MIT) · get_code("178099b1f8fb2b9d")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, linzichuan/sdpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 1 the same month, 5 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
make_output_format 73 other papers
38 dated earlier, 35 later
1611.05763 (2016-11)
Learning to reinforcement learn
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1806.02473 (2018-06)
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
and 70 more not named here
profile 61 other papers
25 dated earlier, 35 later, 1 same year, order not determinable
1611.05763 (2016-11)
Learning to reinforcement learn
1905.06750 (2019-05)
Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation
1906.05841 (2019-06)
Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
and 58 more not named here
read_json 22 other papers
19 dated earlier, 3 later
1611.05763 (2016-11)
Learning to reinforcement learn
1711.00123 (2017-11)
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
and 19 more not named here
register 12 other papers
12 dated earlier
1611.05763 (2016-11)
Learning to reinforcement learn
1708.05144 (2017-08)
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
1905.02363 (2019-05)
Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning
and 9 more not named here
rolling_window 12 other papers
11 dated earlier, 1 later
1611.05763 (2016-11)
Learning to reinforcement learn
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1806.02473 (2018-06)
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
and 9 more not named here
window_func 10 other papers
10 dated earlier
1611.05763 (2016-11)
Learning to reinforcement learn
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1806.02473 (2018-06)
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
and 7 more not named here
cat_entropy_softmax 6 other papers
6 dated earlier
1611.05763 (2016-11)
Learning to reinforcement learn
1711.00123 (2017-11)
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
and 3 more not named here
flat_concat 6 other papers
2 dated earlier, 1 the same month, 3 later
2006.07442 (2020-06)
Self-Imitation Learning via Generalized Lower Bound Q-learning
2210.07573 (2022-10)
Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm
2302.00808 (2023-02)
ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints
and 3 more not named here
sample 6 other papers
6 dated earlier
1611.05763 (2016-11)
Learning to reinforcement learn
1711.00123 (2017-11)
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
and 3 more not named here
cat_entropy 4 other papers
4 dated earlier
1611.05763 (2016-11)
Learning to reinforcement learn
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1905.04100 (2019-05)
Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization
and 1 more not named here
build_impala_cnn 2 other papers
2 dated earlier
1906.05841 (2019-06)
Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
2007.08459 (2020-07)
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 \url{https://github.com/LinZichuan/sdpo.git}.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.02299")
get_code_for_paper("2302.02299")
have("2302.02299")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2302.02299.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2302.02299.svg)](https://syntology.ai/paper/2302.02299)

Connect an agent — have() is free.