[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-10218":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":30,"readmeContent":31,"aiSummary":32,"trendingCount":16,"starSnapshotCount":16,"syncStatus":33,"lastSyncTime":34,"discoverSource":35},10218,"Gymnasium","Farama-Foundation\u002FGymnasium","Farama-Foundation","An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)","https:\u002F\u002Fgymnasium.farama.org",null,"Python",12036,1360,64,76,0,3,38,163,26,44.4,"MIT License",false,"main",true,[27,28,29],"api","gym","reinforcement-learning","2026-06-12 02:02:18","[![Python](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Fgymnasium.svg)](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fgymnasium)\n[![PyPI](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fgymnasium.svg)](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fgymnasium)\n[![arXiv](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FarXiv-2407.17032-b31b1b.svg)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.17032)\n[![pre-commit](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https:\u002F\u002Fpre-commit.com\u002F)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002FFarama-Foundation\u002FGymnasium)](https:\u002F\u002Fgithub.com\u002FFarama-Foundation\u002FGymnasium\u002Fblob\u002Fmain\u002FLICENSE)\n[![Code style: black](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcode%20style-black-000000.svg)](https:\u002F\u002Fgithub.com\u002Fpsf\u002Fblack)\n\n\u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fgymnasium.farama.org\u002F\" target = \"_blank\">\n    \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002FFarama-Foundation\u002FGymnasium\u002Fmain\u002Fgymnasium-text.png\" width=\"500px\" \u002F>\n\u003C\u002Fa>\n\n\u003C\u002Fp>\n\nGymnasium is an open source Python library for developing and comparing reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments, as well as a standard set of environments compliant with that API. This is a fork of OpenAI's [Gym](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fgym) library by its maintainers (OpenAI handed over maintenance a few years ago to an outside team), and is where future maintenance will occur going forward.\n\nThe documentation website is at [gymnasium.farama.org](https:\u002F\u002Fgymnasium.farama.org), and we have a public discord server (which we also use to coordinate development work) that you can join here: https:\u002F\u002Fdiscord.gg\u002FbnJ6kubTg6\n\n## Environments\n\nGymnasium includes the following families of environments along with a wide variety of third-party environments\n* [Classic Control](https:\u002F\u002Fgymnasium.farama.org\u002Fenvironments\u002Fclassic_control\u002F) - These are classic reinforcement learning based on real-world problems and physics.\n* [Box2D](https:\u002F\u002Fgymnasium.farama.org\u002Fenvironments\u002Fbox2d\u002F) - These environments all involve toy games based around physics control, using box2d based physics and PyGame-based rendering\n* [Toy Text](https:\u002F\u002Fgymnasium.farama.org\u002Fenvironments\u002Ftoy_text\u002F) - These environments are designed to be extremely simple, with small discrete state and action spaces, and hence easy to learn. As a result, they are suitable for debugging implementations of reinforcement learning algorithms.\n* [MuJoCo](https:\u002F\u002Fgymnasium.farama.org\u002Fenvironments\u002Fmujoco\u002F) - A physics engine based environments with multi-joint control which are more complex than the Box2D environments.\n* [Atari](https:\u002F\u002Fale.farama.org\u002F) - Emulator of Atari 2600 ROMs simulated that have a high range of complexity for agents to learn.\n* [Third-party](https:\u002F\u002Fgymnasium.farama.org\u002Fenvironments\u002Fthird_party_environments\u002F) - A number of environments have been created that are compatible with the Gymnasium API. Be aware of the version that the software was created for and use the `apply_env_compatibility` in `gymnasium.make` if necessary.\n\n## Installation\n\nTo install the base Gymnasium library, use `pip install gymnasium`\n\nThis does not include dependencies for all families of environments (there's a massive number, and some can be problematic to install on certain systems). You can install these dependencies for one family like `pip install \"gymnasium[atari]\"` or use `pip install \"gymnasium[all]\"` to install all dependencies.\n\nWe support and test for Python 3.10, 3.11, 3.12 and 3.13 on Linux and macOS. We will accept PRs related to Windows, but do not officially support it.\n\n## API\n\nThe Gymnasium API models environments as simple Python `env` classes. Creating environment instances and interacting with them is very simple- here's an example using the \"CartPole-v1\" environment:\n\n```python\nimport gymnasium as gym\nenv = gym.make(\"CartPole-v1\")\n\nobservation, info = env.reset(seed=42)\nfor _ in range(1000):\n    action = env.action_space.sample()\n    observation, reward, terminated, truncated, info = env.step(action)\n\n    if terminated or truncated:\n        observation, info = env.reset()\nenv.close()\n```\n\n## Notable Related Libraries\n\nPlease note that this is an incomplete list, and just includes libraries that the maintainers most commonly point newcomers to when asked for recommendations.\n\n* [CleanRL](https:\u002F\u002Fgithub.com\u002Fvwxyzjn\u002Fcleanrl) is a learning library based on the Gymnasium API. It is designed to cater to newer people in the field and provides very good reference implementations.\n* [PettingZoo](https:\u002F\u002Fgithub.com\u002FFarama-Foundation\u002FPettingZoo) is a multi-agent version of Gymnasium with a number of implemented environments, for example, multi-agent Atari environments.\n* The Farama Foundation also has a collection of many other [environments](https:\u002F\u002Ffarama.org\u002Fprojects) that are maintained by the same team as Gymnasium and use the Gymnasium API.\n\n## Environment Versioning\n\nGymnasium keeps strict versioning for reproducibility reasons. All environments end in a suffix like \"-v0\".  When changes are made to environments that might impact learning results, the number is increased by one to prevent potential confusion. These were inherited from Gym.\n\n## Contributing\n\nWe welcome contributions from the community!\nPlease see our [CONTRIBUTING.md](https:\u002F\u002Fgithub.com\u002FFarama-Foundation\u002FGymnasium\u002Fblob\u002Fmain\u002FCONTRIBUTING.md) for details on how to get started.\n\n## Support Gymnasium's Development\n\nIf you are financially able to do so and would like to support the development of Gymnasium, please join others in the community in [donating to us](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FFarama-Foundation).\n\n## Citation\n\nYou can cite Gymnasium using our related paper (https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.17032) as:\n\n```\n@article{towers2024gymnasium,\n  title={Gymnasium: A Standard Interface for Reinforcement Learning Environments},\n  author={Towers, Mark and Kwiatkowski, Ariel and Terry, Jordan and Balis, John U and De Cola, Gianluca and Deleu, Tristan and Goul{\\~a}o, Manuel and Kallinteris, Andreas and Krimmel, Markus and KG, Arjun and others},\n  journal={arXiv preprint arXiv:2407.17032},\n  year={2024}\n}\n```\n","Gymnasium是一个开源的Python库，用于开发和比较强化学习算法，通过提供一个标准API来促进学习算法与环境之间的通信，并包含一系列符合该API标准的环境。该项目的核心功能包括一套标准化的强化学习环境接口及其实现，支持多种类型的环境如经典控制、Box2D物理游戏、玩具文本问题、MuJoCo多关节控制以及Atari 2600模拟器等，适用于从基础研究到复杂场景下的强化学习实验。Gymnasium适合于希望在统一框架下测试不同强化学习算法的研究人员或开发者使用。",2,"2026-06-11 03:27:18","top_topic"]