SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.04831 · 2023

Cooperative Open-ended Learning Framework for Zero-shot Coordination

arXiv · PDF · Open in the Atlas

Code that ran

9 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 3 have no contract verdict; 6 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/2302.04831.json · badge: /api/ran/2302.04831.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
PKU-Alignment/ProAgent community (classifier label)
classifier basis not recorded on the link
9 ran · 1 no recorded run
FunctionStatusWhere it lives
convert_messages_to_prompt Ran
ran on a synthesized input
PKU-Alignment/ProAgent/src/proagent/utils.py
code served (permissive licence) · get_code("d68e86e16e480219")
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

def convert_messages_to_prompt(messages):
    """
    Converts a list of messages(for chat) to a prompt (for completion) for OpenAI's API.

    :param messages:
    :return: prompt
    """
    prompt = ''
    for message in messages:
        prompt += f"{message['content']}\n"
    return prompt


# Setup code to construct valid arguments
torch.manual_seed(0)

messages = [
    {'content': 'Hello, how are you?'},
    {'content': 'I am doing well, thank you.'},
    {'content': 'What is your name?'}
]

ARGS = {
    'messages': messages
}
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
load_dict_from_file Ran
ran; our contract draft was wrong, not the code
PKU-Alignment/ProAgent/lib/overcooked_ai/overcooked_ai_py/utils.py
code served (permissive licence) · get_code("591c3a0919cdc129")
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 tempfile
import os

# Create a temporary file with a dictionary representation
temp_dir = tempfile.mkdtemp()
filepath = os.path.join(temp_dir, "test_dict.py")

# Write a simple dictionary to the file
test_dict = {
    "key1": "value1",
    "key2": 42,
    "key3": [1, 2, 3],
    "key4": {"nested": "dict"}
}

with open(filepath, 'w') as f:
    f.write(repr(test_dict))

ARGS = {
    "filepath": filepath
}
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
load_dict_from_txt Ran
ran; our contract draft was wrong, not the code
PKU-Alignment/ProAgent/lib/overcooked_ai/overcooked_ai_py/utils.py
code served (permissive licence) · get_code("1db1eb104270f970")
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 tempfile
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
temp_filepath = os.path.join(temp_dir, "test_config")

# Create a valid dict and write it to a .txt file
test_dict = {
    "model_name": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "layers": [64, 128, 256],
    "use_dropout": True
}

# Write the dict to file with .txt extension
with open(temp_filepath + ".txt", "w") as f:
    f.write(str(test_dict))

# Define ARGS with the filename parameter (without .txt extension)
# The function will add .txt via fix_filetype
ARGS = {
    "filename": temp_filepath
}
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
load_pickle Ran
ran; our contract draft was wrong, not the code
PKU-Alignment/ProAgent/lib/overcooked_ai/overcooked_ai_py/utils.py
code served (permissive licence) · get_code("c770dc82622e81c4")
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 tempfile
import pickle
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_data")

# Create and save a pickle file
test_data = {"key": "value", "numbers": [1, 2, 3, 4, 5]}
with open(temp_file + ".pickle", "wb") as f:
    pickle.dump(test_data, f)

ARGS = {
    "filename": temp_file
}
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
profile Ran
ran on a synthesized input
PKU-Alignment/ProAgent/lib/stable-baselines/stable_baselines/logger.py
code served (permissive licence) · get_code("2cc8a7e3737ea737")
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 time
from collections import defaultdict

# Define a simple stand-in class for SeqWriter
class SimpleSeqWriter(object):
    def writeseq(self, seq):
        pass
    
    def close(self):
        pass

# Define a simple stand-in class for KVWriter
class SimpleKVWriter(object):
    def writekvs(self, kvs):
        pass
    
    def close(self):
        pass

# The profile function takes a single parameter: name (str)
# Looking at the function body, it:
# - Takes a name parameter
# - Creates a decorator that wraps functions
# - The decorator uses ProfileKV(name) which adds 'wait_' prefix to the name
# - Returns a decorator function

ARGS = {
    "name": "test_operation"
}
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 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
read_json Ran
ran on a synthesized input
PKU-Alignment/ProAgent/lib/stable-baselines/stable_baselines/logger.py
code served (permissive licence) · get_code("64647496a3527b7b")
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 DataFrame. 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 file with test data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, 'test.jsonl')

# Write some test data to the temporary file
test_data = [
    {'name': 'Alice', 'age': 30, 'city': 'New York'},
    {'name': 'Bob', 'age': 25, 'city': 'Los Angeles'},
    {'name': 'Charlie', 'age': 35, 'city': 'Chicago'}
]

with open(temp_file, 'w') as f:
    for record in test_data:
        f.write(json.dumps(record) + '\n')

ARGS = {
    'fname': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
rolling_window Ran
ran; our contract draft was wrong, not the code
PKU-Alignment/ProAgent/lib/stable-baselines/stable_baselines/results_plotter.py
code served (permissive licence) · get_code("a3fd9c3a978a7624")
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 (4, 3, 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

# Create a simple numpy array for testing
array = np.arange(20, dtype=np.float32).reshape(4, 5)

# Define the window size
window = 3

# Construct the ARGS dictionary
ARGS = {
    "array": array,
    "window": window,
}
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 3, dtype family float, shape (4, 3, 3) — shape (4, 3, 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
ts2xy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PKU-Alignment/ProAgent/lib/stable-baselines/stable_baselines/results_plotter.py
code served (permissive licence) · get_code("9cc2d7b8e6215c80")
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 2, 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 pandas as pd

X_TIMESTEPS = 'timesteps'
X_EPISODES = 'episodes'
X_WALLTIME = 'walltime_hrs'

# Create a small pandas DataFrame with the required columns: 'l', 'r', and 't'
# These correspond to: length (timesteps), reward, and time (seconds)
timesteps_data = {
    'l': np.array([10, 20, 15, 25]),
    'r': np.array([0.5, 1.2, 0.8, 1.5]),
    't': np.array([3600.0, 7200.0, 10800.0, 14400.0])  # seconds
}
timesteps_df = pd.DataFrame(timesteps_data)

ARGS = {
    'timesteps': timesteps_df,
    'xaxis': X_TIMESTEPS
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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
window_func Ran
ran; our contract draft was wrong, not the code
PKU-Alignment/ProAgent/lib/stable-baselines/stable_baselines/results_plotter.py
code served (permissive licence) · get_code("0680d6189aa0a2ff")
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 2, 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

# Create simple numpy arrays for testing
var_1 = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
var_2 = np.array([10.0, 20.0, 30.0, 40.0, 50.0])

# Define the window size
window_size = 3

# Define a function to apply (using numpy.mean as the example)
func_to_apply = np.mean

ARGS = {
    "var_1": var_1,
    "var_2": var_2,
    "window": window_size,
    "func": func_to_apply
}
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 tuple, ndim 2, 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
make_output_format Not yet run
unverified (harvested, no recorded run)
PKU-Alignment/ProAgent/lib/stable-baselines/stable_baselines/logger.py
code served (permissive licence) · get_code("6d3c2b5e4fba7274")
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 10 distinct functions with an identity, 8 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 4 later) and 2 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
load_dict_from_file 3 other papers
1 dated earlier, 2 later
2106.10853 (2021-06)
On the Importance of Environments in Human-Robot Coordination
2310.05208 (2023-10)
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
2502.20073 (2025-02)
Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents
load_dict_from_txt 3 other papers
1 dated earlier, 2 later
2106.10853 (2021-06)
On the Importance of Environments in Human-Robot Coordination
2310.05208 (2023-10)
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
2502.20073 (2025-02)
Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents
load_pickle 3 other papers
1 dated earlier, 2 later
2106.10853 (2021-06)
On the Importance of Environments in Human-Robot Coordination
2310.05208 (2023-10)
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
2502.20073 (2025-02)
Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents
make_output_format 2 other papers
2 dated earlier
2105.13345 (2021-05)
Adversarial Intrinsic Motivation for Reinforcement Learning
2111.03941 (2021-11)
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods
rolling_window 2 other papers
2 dated earlier
2105.13345 (2021-05)
Adversarial Intrinsic Motivation for Reinforcement Learning
2111.03941 (2021-11)
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods
ts2xy 2 other papers
2 dated earlier
2105.13345 (2021-05)
Adversarial Intrinsic Motivation for Reinforcement Learning
2111.03941 (2021-11)
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods
window_func 2 other papers
2 dated earlier
2105.13345 (2021-05)
Adversarial Intrinsic Motivation for Reinforcement Learning
2111.03941 (2021-11)
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods
convert_messages_to_prompt 1 other paper
1 later
2502.20073 (2025-02)
Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents

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

Zero-shot coordination in cooperative artificial intelligence (AI) remains a significant challenge, which means effectively coordinating with a wide range of unseen partners. Previous algorithms have attempted to address this challenge by optimizing fixed objectives within a population to improve strategy or behaviour diversity. However, these approaches can result in a loss of learning and an inability to cooperate with certain strategies within the population, known as cooperative incompatibility. To address this issue, we propose the Cooperative Open-ended LEarning (COLE) framework, which constructs open-ended objectives in cooperative games with two players from the perspective of graph theory to assess and identify the cooperative ability of each strategy. We further specify the framework and propose a practical algorithm that leverages knowledge from game theory and graph theory. Furthermore, an analysis of the learning process of the algorithm shows that it can efficiently overcome cooperative incompatibility. The experimental results in the Overcooked game environment demonstrate that our method outperforms current state-of-the-art methods when coordinating with different-level partners. Our demo is available at https://sites.google.com/view/cole-2023.

For agents

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

get_harvested_code_for_paper("2302.04831")
get_code_for_paper("2302.04831")
have("2302.04831")

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

curl https://syntology.ai/api/ran/2302.04831.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.04831.svg)](https://syntology.ai/paper/2302.04831)

Connect an agent — have() is free.