SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.17032 · NeurIPS · 2024

Gymnasium: A Standardized Interface for Reinforcement Learning Environments

Tristan Deleu, Sander Schulhoff, Omar Younis, Mark Towers, Ariel Kwiatkowski, Jordan Terry, John Balis, Gianluca De Cola, Manuel Goulão, Andreas Neuralshift, Kallinteris, Markus Krimmel, and 5 more

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 0 have no contract verdict; 3 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/2407.17032.json · badge: /api/ran/2407.17032.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
farama-foundation/gymnasium canonical (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
array_short_repr Ran
ran; our contract draft was wrong, not the code
farama-foundation/gymnasium/gymnasium/spaces/box.py
code served (permissive licence) · get_code("67607615f421f548")
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 numpy as np
from numpy.typing import NDArray

# Test case 1: Array where all elements are the same (constant array)
arr1 = np.array([5, 5, 5, 5])

# Test case 2: Array with varying elements
arr2 = np.array([1, 2, 3, 4])

# Test case 3: Empty array
arr3 = np.array([])

# Test case 4: 2D array with all same elements
arr4 = np.array([[7, 7], [7, 7]])

# Test case 5: 2D array with varying elements
arr5 = np.array([[1, 2], [3, 4]])

ARGS = {
    "arr": arr2
}
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 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_env_id Ran
ran; our contract draft was wrong, not the code
farama-foundation/gymnasium/gymnasium/envs/registration.py
code served (permissive licence) · get_code("18244322e87d19cc")
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.

# Set up arguments for get_env_id function

ARGS = {
    "ns": "ALE",
    "name": "Pong",
    "version": 5
}
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
parse_env_id Ran
ran; our contract draft was wrong, not the code
farama-foundation/gymnasium/gymnasium/envs/registration.py
code served (permissive licence) · get_code("1e11ef67aa649739")
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 re
from gymnasium import error

ENV_ID_RE = re.compile('^(?:(?P<namespace>[\\w:-]+)\\/)?(?:(?P<name>[\\w:.-]+?))(?:-v(?P<version>\\d+))?$')

def parse_env_id(env_id: str) -> tuple[str | None, str, int | None]:
    """Parse environment ID string format - ``[namespace/](env-name)[-v(version)]`` where the namespace and version are optional.

    Args:
        env_id: The environment id to parse

    Returns:
        A tuple of environment namespace, environment name and version number

    Raises:
        Error: If the environment id is not valid environment regex
    """
    match = ENV_ID_RE.fullmatch(env_id)
    if not match:
        raise error.Error(f'Malformed environment ID: {env_id}. (Currently all IDs must be of the form [namespace/](env-name)-v(version). (namespace is optional))')
    ns, name, version = match.group('namespace', 'name', 'version')
    if version is not None:
        version = int(version)
    return (ns, name, version)

ARGS = {
    'env_id': 'MyNamespace/CartPole-v1'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gymnasium — 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
find_highest_version Not yet run
unverified (harvested, no recorded run)
farama-foundation/gymnasium/gymnasium/envs/registration.py
code served (permissive licence) · get_code("76253ee0b083670c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 0 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
array_short_repr 1 other paper
1 later
2509.17998 (2025-09)
Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
find_highest_version 1 other paper
1 later
2509.17998 (2025-09)
Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
get_env_id 1 other paper
1 later
2509.17998 (2025-09)
Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
parse_env_id 1 other paper
1 later
2509.17998 (2025-09)
Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs

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

Reinforcement Learning (RL) is a continuously growing field that has the potential to revolutionize many areas of artificial intelligence. However, despite its promise, RL research is often hindered by the lack of standardization in the environment and algorithmic implementations. This makes it difficult for researchers to compare and build upon each other's work, slowing progress in the field. Gymnasium is an open-source library that provides a standardized API for RL environments, aiming to tackle this issue, with over 18 million installations. Gymnasium's main feature is a set of abstractions that allow for wide interoperability between environments and training algorithms, making it easier for researchers to develop and test new environments and/or RL algorithms. In addition, Gymnasium provides a collection of built-in easy-to-use environments, tools for easily customizing environments, and tools to ensure the reproducibility and robustness of RL research. Through this unified framework, Gymnasium significantly streamlines the process of developing and testing RL algorithms, enabling researchers to focus on innovation and less on implementation details. By providing a standardized platform for RL research, Gymnasium helps to drive forward the field of reinforcement learning and unlock its full potential. Gymnasium is available online at https://github.com/Farama-Foundation/Gymnasium with documentation at https://gymnasium.farama.org/.

For agents

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

get_harvested_code_for_paper("2407.17032")
get_code_for_paper("2407.17032")
have("2407.17032")

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

curl https://syntology.ai/api/ran/2407.17032.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.17032.svg)](https://syntology.ai/paper/2407.17032)

Connect an agent — have() is free.