Skip to content
A toolkit for developing and comparing reinforcement learning algorithms.
Branch: master
Clone or download
Pull request Compare This branch is 120 commits behind openai:master.
Type Name Latest commit message Commit time
Failed to load latest commit information.
bin fix mujoco-related build failure Oct 23, 2018
examples cleanup examples/scripts/sim_env, make it python3 compatible Mar 1, 2019
vendor Switch to Docker for tests (openai#285) Aug 10, 2016
.gitignore Fix autodetect dtype warnings (openai#1234) Nov 29, 2018
.travis.yml fix .travis.yml syntax Feb 6, 2019
Makefile Switch to for tests Aug 11, 2016
README.rst fix typos in README Mar 8, 2019
requirements_dev.txt use binary wheels for atari-py and box2d (openai#1183) Oct 2, 2018
test.dockerfile.14.04 test dockerfiles for ubuntu 14.04 and 18.04 (openai#1168) Sep 21, 2018
test.dockerfile.16.04 skip mujoco tests in PRs based on presence of MUJOCO_KEY env variable Oct 25, 2018
test.dockerfile.18.04 skip mujoco tests in PRs based on presence of MUJOCO_KEY env variable Oct 25, 2018
tox.ini python27 tests (openai#1314) Feb 8, 2019
unittest.cfg Capture logs in tests May 16, 2016


Status: Maintenance (expect bug fixes and minor updates)

OpenAI Gym

OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms. This is the gym open-source library, which gives you access to a standardized set of environments.

See What's New section below

gym makes no assumptions about the structure of your agent, and is compatible with any numerical computation library, such as TensorFlow or Theano. You can use it from Python code, and soon from other languages.

If you're not sure where to start, we recommend beginning with the docs on our site. See also the FAQ.

A whitepaper for OpenAI Gym is available at, and here's a BibTeX entry that you can use to cite it in a publication:

  Author = {Greg Brockman and Vicki Cheung and Ludwig Pettersson and Jonas Schneider and John Schulman and Jie Tang and Wojciech Zaremba},
  Title = {OpenAI Gym},
  Year = {2016},
  Eprint = {arXiv:1606.01540},


There are two basic concepts in reinforcement learning: the environment (namely, the outside world) and the agent (namely, the algorithm you are writing). The agent sends actions to the environment, and the environment replies with observations and rewards (that is, a score).

The core gym interface is Env, which is the unified environment interface. There is no interface for agents; that part is left to you. The following are the Env methods you should know:

  • reset(self): Reset the environment's state. Returns observation.
  • step(self, action): Step the environment by one timestep. Returns observation, reward, done, info.
  • render(self, mode='human'): Render one frame of the environment. The default mode will do something human friendly, such as pop up a window.


You can perform a minimal install of gym with:

git clone
cd gym
pip install -e .

If you prefer, you can do a minimal install of the packaged version directly from PyPI:

pip install gym

You'll be able to run a few environments right away:

  • algorithmic
  • toy_text
  • classic_control (you'll need pyglet to render though)

We recommend playing with those environments at first, and then later installing the dependencies for the remaining environments.

Installing everything

To install the full set of environments, you'll need to have some system packages installed. We'll build out the list here over time; please let us know what you end up installing on your platform. Also, take a look at the docker files (test.dockerfile.xx.xx) to see the composition of our CI-tested images.


brew install cmake boost boost-python sdl2 swig wget

On Ubuntu 14.04 (non-mujoco only):

apt-get install libjpeg-dev cmake swig python-pyglet python3-opengl libboost-all-dev \
        libsdl2-2.0.0 libsdl2-dev libglu1-mesa libglu1-mesa-dev libgles2-mesa-dev \
        freeglut3 xvfb libav-tools

On Ubuntu 16.04:

apt-get install -y python-pyglet python3-opengl zlib1g-dev libjpeg-dev patchelf \
        cmake swig libboost-all-dev libsdl2-dev libosmesa6-dev xvfb ffmpeg

On Ubuntu 18.04:

apt install -y python3-dev zlib1g-dev libjpeg-dev cmake swig python-pyglet python3-opengl libboost-all-dev libsdl2-dev \
    libosmesa6-dev patchelf ffmpeg xvfb

MuJoCo has a proprietary dependency we can't set up for you. Follow the instructions in the mujoco-py package for help.

Once you're ready to install everything, run pip install -e '.[all]' (or pip install 'gym[all]').

Supported systems

We currently support Linux and OS X running Python 2.7 or 3.5. Some users on OSX + Python3 may need to run

brew install boost-python --with-python3

If you want to access Gym from languages other than python, we have limited support for non-python frameworks, such as lua/Torch, using the OpenAI Gym HTTP API.

Pip version

To run pip install -e '.[all]', you'll need a semi-recent pip. Please make sure your pip is at least at version 1.5.0. You can upgrade using the following: pip install --ignore-installed pip. Alternatively, you can open and install the dependencies by hand.

Rendering on a server

If you're trying to render video on a server, you'll need to connect a fake display. The easiest way to do this is by running under xvfb-run (on Ubuntu, install the xvfb package):

xvfb-run -s "-screen 0 1400x900x24" bash

Installing dependencies for specific environments

If you'd like to install the dependencies for only specific environments, see We maintain the lists of dependencies on a per-environment group basis.


The code for each environment group is housed in its own subdirectory gym/envs. The specification of each task is in gym/envs/ It's worth browsing through both.


These are a variety of algorithmic tasks, such as learning to copy a sequence.

import gym
env = gym.make('Copy-v0')


The Atari environments are a variety of Atari video games. If you didn't do the full install, you can install dependencies via pip install -e '.[atari]' (you'll need cmake installed) and then get started as follows:

import gym
env = gym.make('SpaceInvaders-v0')

This will install atari-py, which automatically compiles the Arcade Learning Environment. This can take quite a while (a few minutes on a decent laptop), so just be prepared.


Box2d is a 2D physics engine. You can install it via pip install -e '.[box2d]' and then get started as follows:

import gym
env = gym.make('LunarLander-v2')

Classic control

These are a variety of classic control tasks, which would appear in a typical reinforcement learning textbook. If you didn't do the full install, you will need to run pip install -e '.[classic_control]' to enable rendering. You can get started with them via:

import gym
env = gym.make('CartPole-v0')


MuJoCo is a physics engine which can do very detailed efficient simulations with contacts. It's not open-source, so you'll have to follow the instructions in mujoco-py to set it up. You'll have to also run pip install -e '.[mujoco]' if you didn't do the full install.

import gym
env = gym.make('Humanoid-v2')


MuJoCo is a physics engine which can do very detailed efficient simulations with contacts and we use it for all robotics environments. It's not open-source, so you'll have to follow the instructions in mujoco-py to set it up. You'll have to also run pip install -e '.[robotics]' if you didn't do the full install.

import gym
env = gym.make('HandManipulateBlock-v0')

You can also find additional details in the accompanying technical report and blog post. If you use these environments, you can cite them as follows:

  Author = {Matthias Plappert and Marcin Andrychowicz and Alex Ray and Bob McGrew and Bowen Baker and Glenn Powell and Jonas Schneider and Josh Tobin and Maciek Chociej and Peter Welinder and Vikash Kumar and Wojciech Zaremba},
  Title = {Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research},
  Year = {2018},
  Eprint = {arXiv:1802.09464},

Toy text

Toy environments which are text-based. There's no extra dependency to install, so to get started, you can just do:

import gym
env = gym.make('FrozenLake-v0')


See the examples directory.


We are using pytest for tests. You can run them via:


What's new

  • 2019-02-26 (v0.12.0)
    • release mujoco environments v3 with support for gym.make kwargs such as xml_file, ctrl_cost_weight, reset_noise_scale etc
  • 2019-02-06 (v0.11.0)
    • remove gym.spaces.np_random common PRNG; use per-instance PRNG instead.
    • support for kwargs in gym.make
    • lots of bugfixes
  • 2018-02-28: Release of a set of new robotics environments.

  • 2018-01-25: Made some aesthetic improvements and removed unmaintained parts of gym. This may seem like a downgrade in functionality, but it is actually a long-needed cleanup in preparation for some great new things that will be released in the next month.

    • Now your Env and Wrapper subclasses should define step, reset, render, close, seed rather than underscored method names.
    • Removed the board_game, debugging, safety, parameter_tuning environments since they're not being maintained by us at OpenAI. We encourage authors and users to create new repositories for these environments.
    • Changed MultiDiscrete action space to range from [0, ..., n-1] rather than [a, ..., b-1].
    • No more render(close=True), use env-specific methods to close the rendering.
    • Removed scoreboard directory, since site doesn't exist anymore.
    • Moved gym/monitoring to gym/wrappers/monitoring
    • Add dtype to Space.
    • Not using python's built-in module anymore, using gym.logger
  • 2018-01-24: All continuous control environments now use mujoco_py >= 1.50. Versions have been updated accordingly to -v2, e.g. HalfCheetah-v2. Performance should be similar (see but there are likely some differences due to changes in MuJoCo.

  • 2017-06-16: Make env.spec into a property to fix a bug that occurs when you try to print out an unregistered Env.

  • 2017-05-13: BACKWARDS INCOMPATIBILITY: The Atari environments are now at v4. To keep using the old v3 environments, keep gym <= 0.8.2 and atari-py <= 0.0.21. Note that the v4 environments will not give identical results to existing v3 results, although differences are minor. The v4 environments incorporate the latest Arcade Learning Environment (ALE), including several ROM fixes, and now handle loading and saving of the emulator state. While seeds still ensure determinism, the effect of any given seed is not preserved across this upgrade because the random number generator in ALE has changed. The *NoFrameSkip-v4 environments should be considered the canonical Atari environments from now on.

  • 2017-03-05: BACKWARDS INCOMPATIBILITY: The configure method has been removed from Env. configure was not used by gym, but was used by some dependent libraries including universe. These libraries will migrate away from the configure method by using wrappers instead. This change is on master and will be released with 0.8.0.

  • 2016-12-27: BACKWARDS INCOMPATIBILITY: The gym monitor is now a wrapper. Rather than starting monitoring as env.monitor.start(directory), envs are now wrapped as follows: env = wrappers.Monitor(env, directory). This change is on master and will be released with 0.7.0.

  • 2016-11-1: Several experimental changes to how a running monitor interacts with environments. The monitor will now raise an error if reset() is called when the env has not returned done=True. The monitor will only record complete episodes where done=True. Finally, the monitor no longer calls seed() on the underlying env, nor does it record or upload seed information.

  • 2016-10-31: We're experimentally expanding the environment ID format to include an optional username.

  • 2016-09-21: Switch the Gym automated logger setup to configure the root logger rather than just the 'gym' logger.

  • 2016-08-17: Calling close on an env will also close the monitor and any rendering windows.

  • 2016-08-17: The monitor will no longer write manifest files in real-time, unless write_upon_reset=True is passed.

  • 2016-05-28: For controlled reproducibility, envs now support seeding (cf #91 and #135). The monitor records which seeds are used. We will soon add seed information to the display on the scoreboard.

You can’t perform that action at this time.