SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.01500 · 2019

rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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 6 have no contract verdict; 2 failures of our instrument; 2 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/1909.01500.json · badge: /api/ran/1909.01500.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
mariuslindegaard/curiosity_baselines community (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
Improbable-AI/curiosity_baselines community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
akterskii/rlpyt community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
conv2d_output_shape Ran
ran on a synthesized input
Improbable-AI/curiosity_baselines/rlpyt/models/utils.py
code served (permissive licence) · get_code("fc2d9d7f350a539e")
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 int; 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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - h: input height (int)
# - w: input width (int)
# - kernel_size: int or tuple of ints (default 1)
# - stride: int or tuple of ints (default 1)
# - padding: int or tuple of ints (default 0)
# - dilation: int (default 1)

# The function performs a conv2d output shape calculation
# All parameters are used in arithmetic operations
# kernel_size, stride, padding can be int or tuple
# We'll test with basic valid values

ARGS = {
    "h": 32,
    "w": 64,
    "kernel_size": 3,
    "stride": 1,
    "padding": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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 int — 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
default_category_choice Ran
ran on a synthesized input
mariuslindegaard/curiosity_baselines/rlpyt/models/curiosity/online_fuzzy_art.py
code served (permissive licence) · get_code("06fff5432ff7085e")
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 float64, ndim 0, 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

# Analyze the function:
# - pattern: used with fuzzy_and, so needs to be array-like
# - category_w: used with fuzzy_and and max_norm, so needs to be array-like
# - alpha: used in division, so needs to be numeric

# fuzzy_and takes x, y and calls np.min on them, so they should be numpy arrays
# max_norm computes L1 norm (ord=1) on arrays

# Create small distinct-sized numpy arrays
pattern = np.array([0.5, 0.3, 0.7, 0.2])  # shape (4,)
category_w = np.array([0.4, 0.6, 0.1, 0.8])  # shape (4,)
alpha = 0.1  # scalar

ARGS = {
    "pattern": pattern,
    "category_w": category_w,
    "alpha": alpha,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
fuzzy_and Ran
ran on a synthesized input
mariuslindegaard/curiosity_baselines/rlpyt/models/curiosity/fuzzy_art.py
code served (permissive licence) · get_code("0967a632ede688b0")
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 (4,) 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

def fuzzy_and(x, y):
    return np.min(np.array([x, y]), 0)

# Create valid arguments for fuzzy_and
x_val = np.array([0.3, 0.7, 0.5, 0.9])
y_val = np.array([0.6, 0.4, 0.8, 0.2])

ARGS = {
    "x": x_val,
    "y": y_val
}
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 ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) 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
get_category Ran
ran on a synthesized input
mariuslindegaard/curiosity_baselines/graph.py
code served (permissive licence) · get_code("c47f024ee204904a")
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 str. 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 torch

torch.manual_seed(0)

# The function get_category takes one parameter: dirname (a string)
# It checks various string patterns and returns a category string or None

ARGS = {
    'dirname': 'arthl_7'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
max_norm Ran
ran on a synthesized input
mariuslindegaard/curiosity_baselines/rlpyt/models/curiosity/fuzzy_art.py
code served (permissive licence) · get_code("68ccf52cd821bb33")
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 float64, ndim 0, 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

def max_norm(x):
    return np.linalg.norm(x, ord=1)

# Create a small numpy array for testing
x = np.array([1.0, -2.0, 3.0, -4.0])

ARGS = {
    "x": x
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
max_norm Ran
ran on a synthesized input
mariuslindegaard/curiosity_baselines/rlpyt/models/curiosity/online_fuzzy_art.py
code served (permissive licence) · get_code("97382e35222ebaf9")
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 float64, ndim 0, 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
from numpy import linalg as la

torch_seed = 0

# Create a small numpy array to pass to max_norm
x = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])

ARGS = {
    "x": x
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
strip_ddp_state_dict Ran
ran; our contract draft was wrong, not the code
Improbable-AI/curiosity_baselines/rlpyt/models/utils.py
code served (permissive licence) · get_code("6b1cccb4333e7320")
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 dict. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a state dict with both 'module.' prefixed keys and regular keys
# This simulates a DDP state dict that needs cleaning
state_dict = {
    'module.layer1.weight': torch.randn(4, 3),
    'module.layer1.bias': torch.randn(4),
    'module.layer2.weight': torch.randn(5, 4),
    'layer3.weight': torch.randn(6, 5),
    'layer3.bias': torch.randn(6),
}

ARGS = {
    'state_dict': state_dict,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
strip_ddp_state_dict Ran
ran; our contract draft was wrong, not the code
akterskii/rlpyt/rlpyt/models/utils.py
code served (permissive licence) · get_code("1a929bb446f49571")
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 dict. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a sample state_dict with DDP-prefixed keys
state_dict = {
    'module.layer1.weight': torch.randn(4, 3),
    'module.layer1.bias': torch.randn(4),
    'module.layer2.weight': torch.randn(5, 4),
    'layer3.weight': torch.randn(2, 5),  # Already without 'module.' prefix
    'layer3.bias': torch.randn(2),
}

ARGS = {
    'state_dict': state_dict
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
fa_cluster Not yet run
unverified (harvested, no recorded run)
mariuslindegaard/curiosity_baselines/rlpyt/models/curiosity/fuzzy_art.py
code served (permissive licence) · get_code("2bd3443af64af7d2")
How it ran

no invocation recorded.

preprocess Not yet run
unverified (harvested, no recorded run)
mariuslindegaard/curiosity_baselines/graph.py
code served (permissive licence) · get_code("42314ae14e08b822")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
conv2d_output_shape 5 other papers
5 later
1910.13439 (2019-10)
Learning to Manipulate Deformable Objects without Demonstrations
2006.16908 (2020-06)
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
2009.08319 (2020-09)
Decoupling Representation Learning from Reinforcement Learning
and 2 more not named here
strip_ddp_state_dict 5 other papers
5 later
1910.13439 (2019-10)
Learning to Manipulate Deformable Objects without Demonstrations
2006.16908 (2020-06)
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
2009.08319 (2020-09)
Decoupling Representation Learning from Reinforcement Learning
and 2 more not named here

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

Since the recent advent of deep reinforcement learning for game play and simulated robotic control, a multitude of new algorithms have flourished. Most are model-free algorithms which can be categorized into three families: deep Q-learning, policy gradients, and Q-value policy gradients. These have developed along separate lines of research, such that few, if any, code bases incorporate all three kinds. Yet these algorithms share a great depth of common deep reinforcement learning machinery. We are pleased to share rlpyt, which implements all three algorithm families on top of a shared, optimized infrastructure, in a single repository. It contains modular implementations of many common deep RL algorithms in Python using PyTorch, a leading deep learning library. rlpyt is designed as a high-throughput code base for small- to medium-scale research in deep RL. This white paper summarizes its features, algorithms implemented, and relation to prior work, and concludes with detailed implementation and usage notes. rlpyt is available at https://github.com/astooke/rlpyt.

For agents

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

get_harvested_code_for_paper("1909.01500")
get_code_for_paper("1909.01500")
have("1909.01500")

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

curl https://syntology.ai/api/ran/1909.01500.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.01500.svg)](https://syntology.ai/paper/1909.01500)

Connect an agent — have() is free.