# farama-foundation/gymnasium

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/farama-foundation-gymnasium).**

12,050 stars · 1,361 forks · Python · MIT

## Links

- GitHub: https://github.com/Farama-Foundation/Gymnasium
- Homepage: https://gymnasium.farama.org
- awesome-repositories: https://awesome-repositories.com/repository/farama-foundation-gymnasium.md

## Topics

`api` `gym` `reinforcement-learning`

## Description

Gymnasium is a suite of standardized APIs and simulation toolkits used to evaluate agent behavior and benchmark reinforcement learning algorithms. It provides a standardized interface for creating and interacting with simulated environments, enabling the training of reinforcement learning agents through a consistent set of interaction protocols.

The project emphasizes experimental reproducibility through a versioned API and a system for tracking changes to environment logic using version suffixes. This ensures that learning results remain consistent and can be replicated across different software releases.

The toolkit includes a collection of reference simulation tasks across physics, text, and game-based scenarios. It supports vectorized environment execution to collect experience in parallel, as well as wrapper-based logic to modify observations or rewards without altering the primary simulation engine.

## Tags

### Artificial Intelligence & ML

- [Agent Simulation Environments](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-simulation-environments.md) — Provides a toolkit of physics, text, and game-based scenarios to test and evaluate agent behaviors.
- [State-Action-Reward Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/development-runtime-environments/agent-environments/state-action-reward-interfaces.md) — Implements a synchronous cycle where agents provide actions and environments return observations and rewards.
- [Autonomous Agent Simulations](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-agent-simulations.md) — Allows agents to be run through diverse physics, text, and game-based scenarios to evaluate control complexity. ([source](https://github.com/farama-foundation/gymnasium#readme))
- [Performance Benchmarking](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-algorithms/reinforcement-learning-simulators/performance-benchmarking.md) — Provides tools for evaluating and comparing agent performance across a standardized set of simulation environments.
- [Reinforcement Learning Environments](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-environments.md) — Provides a standardized interface for defining state, action, and reward logic to train autonomous agents.
- [RL Reproducibility Standards](https://awesome-repositories.com/f/artificial-intelligence-ml/rl-experiment-configurations/rl-reproducibility-standards.md) — Ensures that RL training trials yield consistent results across different software releases via simulation logic tracking.
- [RL Interface Standards](https://awesome-repositories.com/f/artificial-intelligence-ml/rl-interface-standards.md) — Provides universal communication protocols and API specifications for interactions between reinforcement learning agents and environments. ([source](https://github.com/farama-foundation/gymnasium#readme))
- [RL Reference Environments](https://awesome-repositories.com/f/artificial-intelligence-ml/rl-reference-environments.md) — Provides a collection of established simulation environments following a common API for benchmarking learning algorithms. ([source](https://github.com/farama-foundation/gymnasium#readme))
- [Vectorized Environments](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-environments/vectorized-environments.md) — Provides execution wrappers that run multiple simulation instances in parallel to accelerate experience collection.

### Part of an Awesome List

- [Environment Version Locking](https://awesome-repositories.com/f/awesome-lists/data/experiment-tracking/environment-version-locking.md) — Uses version suffixes in environment names to pin simulation logic and ensure result reproducibility.
- [Machine Learning](https://awesome-repositories.com/f/awesome-lists/ai/machine-learning.md) — Standardized environments for reinforcement learning algorithms.
- [Reinforcement Learning](https://awesome-repositories.com/f/awesome-lists/ai/reinforcement-learning.md) — Standard API for single-agent reinforcement learning environments.

### Development Tools & Productivity

- [Observation and Reward Wrappers](https://awesome-repositories.com/f/development-tools-productivity/environment-logic-extensions/observation-and-reward-wrappers.md) — Includes wrapper-based logic to modify observations or rewards without altering the primary simulation engine.

### Education & Learning Resources

- [RL Simulation Tasks](https://awesome-repositories.com/f/education-learning-resources/educational-resources/reference-and-media/books-docs-reference/code-examples/reference-implementations/rl-simulation-tasks.md) — Ships a comprehensive library of diverse simulation tasks that adhere to a common communication protocol.