Gymnasium/docs/index.md

hide-toc, firstpage, lastpage

hide-toc	firstpage	lastpage
true

Gymnasium is a standard API for reinforcement learning, and a diverse collection of reference environments

   :alt: Lunar Lander
   :width: 500

Gymnasium is a maintained fork of OpenAI’s Gym library. The Gymnasium interface is simple, pythonic, and capable of representing general RL problems:

import gymnasium as gym
env = gym.make("LunarLander-v2", render_mode="human")
observation, info = env.reset(seed=42)
for _ in range(1000):
   action = policy(observation)  # User-defined policy function
   observation, reward, terminated, truncated, info = env.step(action)

   if terminated or truncated:
      observation, info = env.reset()
env.close()

:hidden:
:caption: Introduction

content/basic_usage

:hidden:
:caption: API

api/core
api/spaces
api/wrappers
api/vector
api/utils

:hidden:
:caption: Environments

environments/atari/index
environments/mujoco/index
environments/toy_text/index
environments/classic_control/index
environments/box2d/index
environments/third_party_environments/index

:hidden:
:caption: Tutorials

content/environment_creation
content/vectorising

:hidden:
:caption: Development

Github <https://github.com/Farama-Foundation/Gymnasium>
Donate <https://farama.org/donations>