SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.03772 · 2019

A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 1 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/1909.03772.json · badge: /api/ran/1909.03772.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
dti-research/SenseActExperiments canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
bootstrap Ran
ran on a synthesized input
dti-research/SenseActExperiments/evaluate/evaluate.py
code served (permissive licence) · get_code("72d7383d8fc116f0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function expects:
# - rewards: an iterable of array-like objects (each element should be something we can compute np.mean on)
# - n_resamples: int (optional, default 10000)
# - seed: int or None (optional, default None)

# Create sample reward data - a list of arrays, each representing rewards for a trial/episode
rewards = [
    np.array([1.0, 2.0, 3.0, 4.0]),
    np.array([1.5, 2.5, 3.5]),
    np.array([0.5, 1.5, 2.5, 3.5, 4.5])
]

ARGS = {
    "rewards": rewards,
    "n_resamples": 1000,
    "seed": 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_mean_ci Ran
ran on a synthesized input
dti-research/SenseActExperiments/evaluate/evaluate.py
code served (permissive licence) · get_code("0aa883b0e9f732ae")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import scipy.stats as st

# Create sample data for the function
data = np.array([1.2, 1.5, 1.3, 1.4, 1.6, 1.55, 1.45, 1.35, 1.25, 1.65])

# Define arguments for compute_mean_ci
ARGS = {
    "data": data,
    "confidence": 0.95
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_callback Ran
ran on a synthesized input
dti-research/SenseActExperiments/code/helper.py
code served (permissive licence) · get_code("c95c349d9b6d63e8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import builtins

torch_imported = False
try:
    import torch
    torch_imported = True
    torch.manual_seed(0)
except ImportError:
    pass

# Create a shared_returns dict that the callback will use
shared_returns = {
    'write_lock': False,
    'episodic_returns': [],
    'episodic_lengths': []
}

ARGS = {
    'shared_returns': shared_returns
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_xticks Ran
ran on a synthesized input
dti-research/SenseActExperiments/evaluate/dist_fitter.py
code served (permissive licence) · get_code("80f105a970d9f936")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import matplotlib.pyplot as plt

# Create a simple plot to establish xticks
fig, ax = plt.subplots()
ax.plot([1, 2, 3, 4, 5])
plt.draw()

# Create sample data array
data = np.array([10, 20, 30, 40, 50])

ARGS = {
    "plt": plt,
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (5,) — shape (5,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
read_csv_files Ran
ran on a synthesized input
dti-research/SenseActExperiments/evaluate/dist_fitter.py
code served (permissive licence) · get_code("45b1de17ab516b93")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import numpy as np

# Create a temporary directory with CSV files
temp_dir = tempfile.mkdtemp()

# Create sample CSV files with data
csv_file_1 = os.path.join(temp_dir, 'data1.csv')
with open(csv_file_1, 'w') as f:
    f.write('header1,header2,header3\n')
    f.write('1.0,2.0,3.0\n')
    f.write('4.0,5.0,6.0\n')

csv_file_2 = os.path.join(temp_dir, 'data2.csv')
with open(csv_file_2, 'w') as f:
    f.write('col1,col2,col3\n')
    f.write('7.0,8.0,9.0\n')
    f.write('10.0,11.0,12.0\n')

ARGS = {
    'path': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
read_csv_files Ran
ran on a synthesized input
dti-research/SenseActExperiments/evaluate/evaluate.py
code served (permissive licence) · get_code("16373edbff04e2aa")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import numpy as np

# Create a temporary directory with CSV files
temp_dir = tempfile.mkdtemp()

# Create a few sample CSV files with numeric data
csv_file_1 = os.path.join(temp_dir, "data1.csv")
with open(csv_file_1, 'w') as f:
    f.write("header1,header2,header3\n")
    f.write("1.0,2.0,3.0\n")
    f.write("4.0,5.0,6.0\n")

csv_file_2 = os.path.join(temp_dir, "data2.csv")
with open(csv_file_2, 'w') as f:
    f.write("col1,col2\n")
    f.write("7.0,8.0\n")
    f.write("9.0,10.0\n")

csv_file_3 = os.path.join(temp_dir, "data3.csv")
with open(csv_file_3, 'w') as f:
    f.write("x,y,z\n")
    f.write("11.0,12.0,13.0\n")

ARGS = {
    "path": temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
read_csv_files Ran
ran on a synthesized input
dti-research/SenseActExperiments/evaluate/plot_w_std_dev.py
code served (permissive licence) · get_code("61a80260f7ad4bf9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import numpy as np

# Create a temporary directory with sample CSV files
temp_dir = tempfile.mkdtemp()

# Create first CSV file with header and data
csv_file_1 = os.path.join(temp_dir, 'data1.csv')
with open(csv_file_1, 'w') as f:
    f.write('col1,col2,col3\n')
    f.write('1.0,2.0,3.0\n')
    f.write('4.0,5.0,6.0\n')

# Create second CSV file with header and data
csv_file_2 = os.path.join(temp_dir, 'data2.csv')
with open(csv_file_2, 'w') as f:
    f.write('col1,col2,col3\n')
    f.write('7.0,8.0,9.0\n')
    f.write('10.0,11.0,12.0\n')

ARGS = {
    'path': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
fit_distributions Not yet run
unverified (harvested, no recorded run)
dti-research/SenseActExperiments/evaluate/dist_fitter.py
code served (permissive licence) · get_code("a30533080afa3611")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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.

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

As reinforcement learning (RL) achieves more success in solving complex tasks, more care is needed to ensure that RL research is reproducible and that algorithms herein can be compared easily and fairly with minimal bias. RL results are, however, notoriously hard to reproduce due to the algorithms' intrinsic variance, the environments' stochasticity, and numerous (potentially unreported) hyper-parameters. In this work we investigate the many issues leading to irreproducible research and how to manage those. We further show how to utilise a rigorous and standardised evaluation approach for easing the process of documentation, evaluation and fair comparison of different algorithms, where we emphasise the importance of choosing the right measurement metrics and conducting proper statistics on the results, for unbiased reporting of the results.

For agents

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

get_harvested_code_for_paper("1909.03772")
get_code_for_paper("1909.03772")
have("1909.03772")

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

curl https://syntology.ai/api/ran/1909.03772.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.03772.svg)](https://syntology.ai/paper/1909.03772)

Connect an agent — have() is free.