SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.00397 · 2018

Visual Transfer between Atari Games using Competitive Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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 5 have no contract verdict; 1 failure of our instrument; 3 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/1809.00397.json · badge: /api/ran/1809.00397.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
sowmya-mp/rl_a3c_pytorch canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
dist_exp Ran
ran on a synthesized input
sowmya-mp/rl_a3c_pytorch/transfer_util.py
code served (permissive licence) · get_code("6159e3123fa29aff")
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 2, dtype family int, shape (2, 3) 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

# The function dist_exp takes an image (im) as input
# It applies exponential transformation and scaling
# im should be a numpy array of numeric values

# Create a small test image
test_image = np.array([
    [0.0, 12.0, 24.0],
    [36.0, 48.0, 60.0]
], dtype=np.float32)

ARGS = {
    "im": test_image
}
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 2, dtype family int, shape (2, 3) — shape (2, 3) 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
frame2attention Ran
ran on a synthesized input
sowmya-mp/rl_a3c_pytorch/transfer_util.py
code served (permissive licence) · get_code("eca1e5a3b68e3b7e")
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. 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 numpy as np
import cv2

# Create a dummy frame - needs to be larger than the crop region
# config['crop1']:config['crop2'] + 160 will crop vertically
# then [:160] crops horizontally
# So we need at least (crop2 + 160) height and 160+ width
frame = np.random.randint(0, 256, (400, 200, 3), dtype=np.uint8)

# Create config dict with required keys
config = {
    'crop1': 50,
    'crop2': 100
}

# Environment string that determines behavior
environment = "Atari-v0"

ARGS = {
    'frame': frame,
    'config': config,
    'environment': environment
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
get_translator Ran
ran on a synthesized input
sowmya-mp/rl_a3c_pytorch/utils.py
code served (permissive licence) · get_code("199fa38db394006c")
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 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 torch.nn as nn

class Args:
    def __init__(self, model_env, env):
        self.model_env = model_env
        self.env = env

ARGS = {
    'args': Args(model_env='Tennis', env='Pong')
}
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 list, ndim 1, dtype family int — 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
get_translator_from_source Ran
ran on a synthesized input
sowmya-mp/rl_a3c_pytorch/utils.py
code served (permissive licence) · get_code("e3b70291f153e3ec")
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 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

# Analyzing the function: get_translator_from_source takes two string parameters
# and returns a list based on conditional checks on the strings.
# The function only uses string operations (checking if substrings are in the parameters).

# Test cases for different branches:
ARGS = {
    "source": "Tennis",
    "target": "DemonAttack"
}
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 list, ndim 1, dtype family int — 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
process_frame Ran
ran on a synthesized input
sowmya-mp/rl_a3c_pytorch/environment.py
code served (permissive licence) · get_code("adfd6d9f5bdf1dda")
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 3, dtype family float, shape (1, 80, 80) 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

# Create a sample frame: (height, width, channels)
# Using distinct dimensions: 120x160x3 to avoid ambiguity
frame = np.random.randint(0, 256, size=(120, 160, 3), dtype=np.uint8)

# Create a config dict with the required 'dimension2' key
conf = {
    'dimension2': 80
}

ARGS = {
    'frame': frame,
    'conf': conf
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (1, 80, 80) — shape (1, 80, 80) 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_config Ran
ran; our contract draft was wrong, not the code
sowmya-mp/rl_a3c_pytorch/utils.py
code served (permissive licence) · get_code("4000c95fa330f2ce")
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 json
import tempfile
import os

# Create a temporary JSON config file
temp_dir = tempfile.mkdtemp()
config_file_path = os.path.join(temp_dir, "config.json")

config_data = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "layers": [64, 128, 256]
}

with open(config_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    "file_path": config_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
atari_env Not yet run
unverified (harvested, no recorded run)
sowmya-mp/rl_a3c_pytorch/environment.py
code served (permissive licence) · get_code("ea979459df3a4fdf")
How it ran

no invocation recorded.

create_xy_image Not yet run
unverified (harvested, no recorded run)
sowmya-mp/rl_a3c_pytorch/transfer_util.py
code served (permissive licence) · get_code("d3883758a6f28097")
How it ran

no invocation recorded.

make_dot Not yet run
unverified (harvested, no recorded run)
sowmya-mp/rl_a3c_pytorch/visualize.py
code served (permissive licence) · get_code("1db353764a69ff91")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 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 (1 with at least one paper dated earlier, 0 the same month, 1 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
read_config 5 other papers
5 later
2002.03519 (2020-02)
Self-Attentive Associative Memory
2008.01976 (2020-08)
Robust Deep Reinforcement Learning through Adversarial Loss
2402.02165 (2024-02)
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
and 2 more not named here
make_dot 1 other paper
1 dated earlier
1803.06815 (2018-03)
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

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

This paper explores the use of deep reinforcement learning agents to transfer knowledge from one environment to another. More specifically, the method takes advantage of asynchronous advantage actor critic (A3C) architecture to generalize a target game using an agent trained on a source game in Atari. Instead of fine-tuning a pre-trained model for the target game, we propose a learning approach to update the model using multiple agents trained in parallel with different representations of the target game. Visual mapping between video sequences of transfer pairs is used to derive new representations of the target game; training on these visual representations of the target game improves model updates in terms of performance, data efficiency and stability. In order to demonstrate the functionality of the architecture, Atari games Pong-v0 and Breakout-v0 are being used from the OpenAI gym environment; as the source and target environment.

For agents

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

get_harvested_code_for_paper("1809.00397")
get_code_for_paper("1809.00397")
have("1809.00397")

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

curl https://syntology.ai/api/ran/1809.00397.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.00397.svg)](https://syntology.ai/paper/1809.00397)

Connect an agent — have() is free.