SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.02448 · 2018

Deep Reinforcement Learning for General Video Game AI

arXiv · PDF · Open in the Atlas

Code that ran

10 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; 4 failures of our instrument; 0 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/1806.02448.json · badge: /api/ran/1806.02448.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
rubenrtorrado/GVGAI_GYM canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
Bam4d/GVGAI_GYM community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
IntKeyValuePairEnd Ran
ran on a synthesized input
Bam4d/GVGAI_GYM/python/gvgai/gvgai/client/serialization/IntKeyValuePair.py
code served (permissive licence) · get_code("067f83e182cbf257")
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 numpy as np

# This function expects a 'builder' object that has an EndObject method
# Based on the function body, it simply calls builder.EndObject()
# We need to create a mock builder object with this method

class MockBuilder:
    def __init__(self):
        self.state = "started"
    
    def EndObject(self):
        self.state = "ended"
        return {"status": "object_ended"}

builder = MockBuilder()

ARGS = {
    "builder": builder
}
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 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
ObservationEnd Ran
ran on a synthesized input
Bam4d/GVGAI_GYM/python/gvgai/gvgai/client/serialization/Observation.py
code served (permissive licence) · get_code("4bf20859652f3890")
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 int, ndim 0, dtype family int, shape () 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 torch
import numpy as np

class MockBuilder:
    """Mock builder class that simulates FlatBuffers builder behavior"""
    def __init__(self):
        self.objects = []
        self.current_object = {}
    
    def EndObject(self):
        """Ends the current object and returns an object reference"""
        result = len(self.objects)
        self.objects.append(self.current_object)
        self.current_object = {}
        return result

builder = MockBuilder()

ARGS = {
    "builder": builder
}
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 int, ndim 0, dtype family int, shape () — shape () 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
StateStartImageArrayVector Ran
ran on a synthesized input
Bam4d/GVGAI_GYM/python/gvgai/gvgai/client/serialization/State.py
code served (permissive licence) · get_code("6f0cb6ad3500b95b")
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 int, ndim 0, dtype family int, shape () 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 torch
import numpy as np

# This function appears to be part of FlatBuffers builder API
# We need to create a mock builder object that has a StartVector method

class MockFlatBuffersBuilder:
    def __init__(self):
        self.vectors = []
    
    def StartVector(self, element_size, num_elements, alignment):
        """Mock implementation of FlatBuffers StartVector method"""
        # Store the vector parameters
        vector_info = {
            'element_size': element_size,
            'num_elements': num_elements,
            'alignment': alignment
        }
        self.vectors.append(vector_info)
        return len(self.vectors) - 1

# Create builder instance
builder = MockFlatBuffersBuilder()

# Define arguments
ARGS = {
    'builder': builder,
    'numElems': 5
}
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 int, ndim 0, dtype family int, shape () — shape () 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
StateStartTileArrayVector Ran
ran on a synthesized input
Bam4d/GVGAI_GYM/python/gvgai/gvgai/client/serialization/State.py
code served (permissive licence) · get_code("9a14c9e2c53a77f1")
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 int, ndim 0, dtype family int, shape () 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 torch
import numpy as np

# Mock builder class that has a StartVector method
class MockFlatBufferBuilder:
    def StartVector(self, element_size, num_elements, alignment):
        """Mock implementation of StartVector that returns a vector offset"""
        return num_elements * element_size

builder = MockFlatBufferBuilder()
numElems = 5

ARGS = {
    "builder": builder,
    "numElems": numElems
}
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 int, ndim 0, dtype family int, shape () — shape () 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
StateStartWorldDimensionVector Ran
ran on a synthesized input
Bam4d/GVGAI_GYM/python/gvgai/gvgai/client/serialization/State.py
code served (permissive licence) · get_code("e693dd7cd39ced2b")
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 int, ndim 0, dtype family int, shape () 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 torch
import numpy as np

# This function uses a FlatBuffers builder pattern
# We need to create a mock builder that has a StartVector method
class MockFlatBuffersBuilder:
    def __init__(self):
        self.buffers = []
    
    def StartVector(self, elementSize, numElements, alignment):
        """
        Mock StartVector method that mimics FlatBuffers builder behavior.
        elementSize: size of each element in bytes
        numElements: number of elements in the vector
        alignment: alignment requirement in bytes
        Returns a vector offset or similar identifier
        """
        vector_info = {
            'elementSize': elementSize,
            'numElements': numElements,
            'alignment': alignment
        }
        self.buffers.append(vector_info)
        return len(self.buffers) - 1

builder = MockFlatBuffersBuilder()
numElems = 5

ARGS = {
    'builder': builder,
    'numElems': numElems
}
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 int, ndim 0, dtype family int, shape () — shape () 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
Vector2dEnd Ran
ran on a synthesized input
Bam4d/GVGAI_GYM/python/gvgai/gvgai/client/serialization/Vector2d.py
code served (permissive licence) · get_code("e1d5f00ef0272e71")
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 numpy as np

# The function Vector2dEnd only calls builder.EndObject()
# So we need a builder object with an EndObject method that returns something

class MockBuilder:
    def __init__(self):
        self.state = "initialized"
    
    def EndObject(self):
        return {"result": "vector_2d_end_completed"}

builder = MockBuilder()

ARGS = {
    "builder": builder
}
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 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
compare Ran
ran; our contract draft was wrong, not the code
rubenrtorrado/GVGAI_GYM/gym_gvgai/envs/gvgai/check_build.py
code served (permissive licence) · get_code("606ee3293f860d2f")
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 bool, ndim 0, dtype family float, shape () 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 torch
import numpy as np

torch.manual_seed(0)

# The function compare(hash1, hash2) converts both arguments to frozensets
# and checks equality. So hash1 and hash2 should be hashable iterables
# (lists, tuples, sets, etc.) that can be converted to frozensets.

# Create two different hashable iterables
hash1 = [1, 2, 3, 4]
hash2 = [4, 3, 2, 1]

ARGS = {
    "hash1": hash1,
    "hash2": hash2,
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
dirHash Ran
ran; our contract draft was wrong, not the code
rubenrtorrado/GVGAI_GYM/gym_gvgai/envs/gvgai/check_build.py
code served (permissive licence) · get_code("a2ce8f3431500582")
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 os
import tempfile
import shutil

# Create a temporary directory with some .java files for testing
temp_dir = tempfile.mkdtemp()

# Create some subdirectories and .java files
os.makedirs(os.path.join(temp_dir, "src"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "src", "subdir"), exist_ok=True)

# Write test .java files
with open(os.path.join(temp_dir, "src", "Test1.java"), "w") as f:
    f.write("public class Test1 { }")

with open(os.path.join(temp_dir, "src", "subdir", "Test2.java"), "w") as f:
    f.write("public class Test2 { }")

# Also write a non-.java file that should be ignored
with open(os.path.join(temp_dir, "src", "readme.txt"), "w") as f:
    f.write("This should be ignored")

ARGS = {
    "dirpath": temp_dir
}
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 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
fileHash Ran
ran; our contract draft was wrong, not the code
rubenrtorrado/GVGAI_GYM/gym_gvgai/envs/gvgai/check_build.py
code served (permissive licence) · get_code("5ab6d28b05916db8")
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 tempfile
import os

# Create a temporary file with some content for testing
temp_dir = tempfile.mkdtemp()
test_file = os.path.join(temp_dir, "test.txt")
with open(test_file, 'wb') as f:
    f.write(b"Hello, this is test content for hashing.")

ARGS = {
    'filepath': test_file,
    'blocksize': 4096
}
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 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
get_src Ran
ran; our contract draft was wrong, not the code
rubenrtorrado/GVGAI_GYM/build.py
code served (permissive licence) · get_code("b9479826c3f56102")
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 os
import tempfile
import shutil

# Create a temporary directory structure with .java files
temp_dir = tempfile.mkdtemp()
os.makedirs(os.path.join(temp_dir, "src", "main", "java"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "src", "test"), exist_ok=True)

# Create some .java files
with open(os.path.join(temp_dir, "src", "main", "java", "HelloWorld.java"), "w") as f:
    f.write("public class HelloWorld {}")

with open(os.path.join(temp_dir, "src", "main", "java", "Utils.java"), "w") as f:
    f.write("public class Utils {}")

with open(os.path.join(temp_dir, "src", "test", "TestMain.java"), "w") as f:
    f.write("public class TestMain {}")

# Create some non-.java files that should be ignored
with open(os.path.join(temp_dir, "src", "main", "java", "config.xml"), "w") as f:
    f.write("<config></config>")

with open(os.path.join(temp_dir, "README.md"), "w") as f:
    f.write("# Project")

ARGS = {
    "path": temp_dir
}
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 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

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 10 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 6 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
compare 1 other paper
1 later
2602.00190 (2026-02)
From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models
dirHash 1 other paper
1 later
2602.00190 (2026-02)
From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models
fileHash 1 other paper
1 later
2602.00190 (2026-02)
From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models
get_src 1 other paper
1 later
2602.00190 (2026-02)
From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models

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

The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward model that allows the use of algorithms such as Monte Carlo Tree Search. In this paper, we describe how we interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems. Using this interface, we characterize how widely used implementations of several deep reinforcement learning algorithms fare on a number of GVGAI games. We further analyze the results to provide a first indication of the relative difficulty of these games relative to each other, and relative to those in the Arcade Learning Environment under similar conditions.

For agents

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

get_harvested_code_for_paper("1806.02448")
get_code_for_paper("1806.02448")
have("1806.02448")

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

curl https://syntology.ai/api/ran/1806.02448.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.02448.svg)](https://syntology.ai/paper/1806.02448)

Connect an agent — have() is free.