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, and has a compatibility wrapper for old Gym environments:

import gymnasium as gym
env = gym.make("LunarLander-v2", render_mode="human")
observation, info = env.reset(seed=42)
for _ in range(1000):
   action = env.action_space.sample()  # this is where you would insert your policy
   observation, reward, terminated, truncated, info = env.step(action)

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

:hidden:
:caption: Introduction

content/basic_usage
content/gym_compatibility
content/migration-guide

:hidden:
:caption: API

api/env
api/registry
api/spaces
api/wrappers
api/vector
api/utils
api/experimental

:hidden:
:caption: Environments

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

:hidden:
:glob:
:caption: Tutorials

tutorials/**/index

:hidden:
:caption: Development

Github <https://github.com/Farama-Foundation/Gymnasium>
release_notes/index
Contribute to the Docs <https://github.com/Farama-Foundation/Gymnasium/blob/main/docs/README.md>