Gymnasium 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://github.com/openai/gym) library by it's maintainers (OpenAI handed over maintenance a few years ago to an outside team), and is where future maintenance will occur going forward.
The documentation website is at [gymnasium.farama.org](https://gymnasium.farama.org), and we have a public discord server (which we also use to coordinate development work) that you can join here: https://discord.gg/bnJ6kubTg6
Gymnasium includes the following families of environments along with a wide variety of third-party environments
* [Classic Control](https://gymnasium.farama.org/environments/classic_control/) - These are classic reinforcement learning based on real-world problems and physics.
* [Box2D](https://gymnasium.farama.org/environments/box2d/) - These environments all involve toy games based around physics control, using box2d based physics and PyGame-based rendering
* [Toy Text](https://gymnasium.farama.org/environments/toy_text/) - 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.
* [MuJoCo](https://gymnasium.farama.org/environments/mujoco/) - A physics engine based environments with multi-joint control which are more complex than the Box2D environments.
* [Atari](https://gymnasium.farama.org/environments/atari/) - A set of 57 Atari 2600 environments simulated through Stella and the Arcade Learning Environment that have a high range of complexity for agents to learn.
* [Third-party](https://gymnasium.farama.org/environments/third_party_environments/) - 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.
This 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.
The 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:
Please note that this is an incomplete list, and just includes libraries that the maintainers most commonly point newcommers to when asked for recommendations.
* [CleanRL](https://github.com/vwxyzjn/cleanrl) 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.
* [PettingZoo](https://github.com/Farama-Foundation/PettingZoo) is a multi-agent version of Gymnasium with a number of implemented environments, i.e. multi-agent Atari environments.
* The Farama Foundation also has a collection of many other [environments](https://farama.org/projects) that are maintained by the same team as Gymnasium and use the Gymnasium API.
Gymnasium 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 inherent from Gym.
