Need help with universe?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

7.3K Stars 908 Forks MIT License 210 Commits 0 Opened issues


Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

Services available


Need anything else?

Contributors list

This repository has been deprecated in favor of the Retro ( library. See our Retro Contest ( blog post for detalis.


_ is a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications. This is the
open-source library, which provides a simple
__ interface to each Universe environment.

Universe allows anyone to train and evaluate AI agents on an extremely wide range of real-time, complex environments.

Universe makes it possible for any existing program to become an OpenAI Gym environment, without needing special access to the program's internals, source code, or APIs. It does this by packaging the program into a Docker container, and presenting the AI with the same interface a human uses: sending keyboard and mouse events, and receiving screen pixels. Our initial release contains over 1,000 environments in which an AI agent can take actions and gather observations.

Additionally, some environments include a reward signal sent to the agent, to guide reinforcement learning. We've included a few hundred environments with reward signals. These environments also include automated start menu clickthroughs, allowing your agent to skip to the interesting part of the environment.

We'd like the community's

_ to grow the number of available environments, including integrating increasingly large and complex games.

The following classes of tasks are packaged inside of publicly-available Docker containers, and can be run today with no work on your part:

  • Atari and CartPole environments over VNC:
    , etc.
  • Flashgames over VNC:
    , etc.
  • Browser tasks ("World of Bits") over VNC:
    , etc.

We've scoped out integrations for many other games, including completing a high-quality GTA V integration (thanks to

Craig Quiter 
_ and NVIDIA), but these aren't included in today's release.

.. contents:: Contents of this document :depth: 2

Getting started


Supported systems ~~~~~~~~~~~~~~~~~

We currently support Linux and OSX running Python 2.7 or 3.5.

We recommend setting up a

conda environment 
__ before getting started, to keep all your Universe-related packages in the same place.

Install Universe ~~~~~~~~~~~~~~~~ To get started, first install


.. code:: shell

git clone
cd universe
pip install -e .

If this errors out, you may be missing some required packages. Here's the list of required packages we know about so far (please let us know if you had to install any others).

On Ubuntu 16.04:

.. code:: shell

pip install numpy
sudo apt-get install golang libjpeg-turbo8-dev make

On Ubuntu 14.04:

.. code:: shell

sudo add-apt-repository ppa:ubuntu-lxc/lxd-stable  # for newer golang
sudo apt-get update
sudo apt-get install golang libjpeg-turbo8-dev make


You might need to install Command Line Tools by running:

.. code:: shell

xcode-select --install



.. code:: shell

pip install numpy incremental
brew install golang libjpeg-turbo

Install Docker ~~~~~~~~~~~~~~

The majority of the environments in Universe run inside Docker containers, so you will need to

install Docker
__ (on OSX, we recommend
Docker for Mac
__). You should be able to run
docker ps
and get something like this:

.. code:: shell

 $ docker ps
 CONTAINER ID        IMAGE               COMMAND             CREATED             STATUS              PORTS               NAMES

Alternate configuration - running the agent in docker ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The above instructions result in an agent that runs as a regular python process in your OS, and launches docker containers as needed for the remotes. Alternatively, you can build a docker image for the agent and run it as a container as well. You can do this in any operating system that has a recent version of docker installed, and the git client.

To get started, clone the


.. code:: shell

git clone
cd universe

Build a docker image, tag it as 'universe':

.. code:: shell

docker build -t universe .

This may take a while the first time, as the docker image layers are pulled from docker hub.

Once the image is built, you can do a quick run of the test cases to make sure everything is working:

.. code:: shell

docker run --privileged --rm -e DOCKER_NET_HOST= -v /var/run/docker.sock:/var/run/docker.sock universe pytest

Here's a breakdown of that command:

  • docker run
    - launch a docker container
  • --rm
    - delete the container once the launched process finishes
    - tells the universe remote (when launched) to make its VNC connection back to this docker-allocated IP
  • -v /var/run/docker.sock:/var/run/docker.sock
    - makes the docker unix socket from the host available to the container. This is a common technique used to allow containers to launch other containers alongside itself.
  • universe
    - use the imaged named 'universe' built above
  • pytest
    - run 'pytest' in the container, which runs all the tests

At this point, you'll see a bunch of tests run and hopefully all pass.

To do some actual development work, you probably want to do another volume map from the universe repo on your host into the container, then shell in interactively:

.. code:: shell

docker run --privileged --rm -it -e DOCKER_NET_HOST= -v /var/run/docker.sock:/var/run/docker.sock -v (full path to cloned repo above):/usr/local/universe universe python

As you edit the files in your cloned git repo, they will be changed in your docker container and you'll be able to run them in python.

Note if you are using docker for Windows, you'll need to enable the relevant shared drive for this to work.

Notes on installation ~~~~~~~~~~~~~~~~~~~~~

  • When installing
    , you may see
    messages. These lines occur when installing numpy and are normal.
  • You'll need a
    go version
    of at least 1.5. Ubuntu 14.04 has an older Go, so you'll need to
    _ your Go installation.
  • We run Python 3.5 internally, so the Python 3.5 variants will be much more thoroughly performance tested. Please let us know if you see any issues on 2.7.
  • While we don't officially support Windows, we expect our code to be very close to working there. We'd be happy to take pull requests that take our Windows compatibility to 100%. In the meantime, the easiest way for Windows users to run universe is to use the alternate configuration described above.

System overview

A Universe environment is similar to any other Gym environment: the agent submits actions and receives observations using the


Internally, a Universe environment consists of two pieces: a client and a remote:

  • The client is a
    _ instance which lives in the same process as the agent. It performs functions like receiving the agent's actions, proxying them to the remote, queuing up rewards for the agent, and maintaining a local view of the current episode state.
  • The remote is the running environment dynamics, usually a program running inside of a Docker container. It can run anywhere -- locally, on a remote server, or in the cloud. (We have a separate page describing how to manage
  • The client and the remote communicate with one another using the
    __ remote desktop system, as well as over an auxiliary WebSocket channel for reward, diagnostic, and control messages. (For more information on client-remote communication, see the separate page on the
    Universe internal communication protocols

The code in this repository corresponds to the client side of the Universe environments. Additionally, you can freely access the Docker images for the remotes. We'll release the source repositories for the remotes in the future, along with tools to enable users to integrate new environments. Please sign up for our

_ if you'd like early access.

Run your first agent

Now that you've installed the

library, you should make sure it actually works. You can paste the example below into your
REPL. (You may need to press enter an extra time to make sure the
loop is executing.)

.. code:: python

import gym import universe # register the universe environments

env = gym.make('flashgames.DuskDrive-v0') env.configure(remotes=1) # automatically creates a local docker container observation_n = env.reset()

while True: actionn = [[('KeyEvent', 'ArrowUp', True)] for ob in observationn] # your agent here observationn, rewardn, donen, info = env.step(actionn) env.render()

The example will instantiate a client in your Python process, automatically pull the
image, and will start that image as the remote. (In our
__ documentation page, we explain other ways you can run remotes.)

It will take a few minutes for the image to pull the first time. After that, if all goes well, a window like the one below will soon pop up. Your agent, which is just pressing the up arrow repeatedly, is now playing a Flash racing game called

Dusk Drive
__. Your agent is programmatically controlling a VNC client, connected to a VNC server running inside of a Docker container in the cloud, rendering a headless Chrome with Flash enabled:

.. image:: :width: 600px

You can even connect your own VNC client to the environment, either just to observe or to interfere with your agent. Our

images conveniently bundle a browser-based VNC client, which can be accessed at
. If you're on Mac, connecting to a VNC server is as easy as running:

(If using docker-machine, you'll need to replace "localhost" with the IP address of your Docker daemon, and use

as the password.)

Breaking down the example ~~~~~~~~~~~~~~~~~~~~~~~~~

So we managed to run an agent, what did all the code actually mean? We'll go line-by-line through the example.

  • First, we import the
    __ library, which is the base on which Universe is built. We also import
    , which
    __ all the Universe environments.

.. code:: python

import gym import universe # register the universe environments

  • Next, we create the environment instance. Behind the scenes,
    looks up the
    __ for
    , and instantiates a
    __ object which has been
    __ to add a few useful diagnostics and utilities. The
    object is the client part of the environment, and it is not yet connected to a remote.

.. code:: python

env = gym.make('flashgames.DuskDrive-v0')

  • The call to
    connects the client to a remote environment server. When called with
    , Universe will automatically create a Docker image running locally on your computer. The local client connects to the remote using VNC. (More information on client-remote communication can be found in the page on
    universe internal communication protocols
    . More on configuring remotes is at

.. code:: python


  • When starting a new environment, you call
    . Universe environments run in real-time, rather than stepping synchronously with the agent's actions, so
    is asynchronous and returns immediately. Since the environment will not have waited to finish connecting to the VNC server before returning, the initial observations from
    will be
    to indicate that there is not yet a valid observation.

Similarly, the environment keeps running in the background even if the agent does not call

. This means that an agent that successfully learns from a Universe environment cannot take "thinking breaks": it must keep sending actions to the environment at all times.

Additionally, Universe introduces the vectorized Gym API. Rather than controlling a single environment at a time, the agent can control a fixed-size vector of

environments, each with its own remote. The return value from
is therefore a vector of observations. For more information, see the separate page on
environment semantics 

.. code:: python

observation_n = env.reset()

  • At each
    call, the agent submits a vector of actions; one for each environment instance it is controlling. Each VNC action is a list of events; above, each action is the single event "press the
    key". The agent could press and release the key in one action by instead submitting
    [('KeyEvent', 'ArrowUp', True),
    ('KeyEvent', 'ArrowUp', False)]
    for each observation.

In fact, the agent could largely have the same effect by just submitting

('KeyEvent', 'ArrowUp', True)
once and then calling
env.step([[] for ob in observation_n])
thereafter, without ever releasing the key using
('KeyEvent', 'ArrowUp', False)
. The browser running inside the remote would continue to statefully represent the arrow key as being pressed. Sending other unrelated keypresses would not disrupt the up arrow keypress; only explicitly releasing the key would cancel it. There's one slight subtlety: when the episode resets, the browser will reset, and will forget about the keypress; you'd need to submit a new
at the start of each episode.

.. code:: python

actionn = [[('KeyEvent', 'ArrowUp', True)] for ob in observationn]

  • After we submit the action to the environment and render one frame,
    returns a list of observations, a list of rewards, a list of "done" booleans indicating whether the episode has ended, and then finally an info dictionary of the form
    {'n': [{},
    , in which you can access the info for environment

Each environment's

message contains useful diagnostic information, including latency data, client and remote timings, VNC update counts, and reward message counts.

.. code:: python

observation_n, reward_n, done_n, info = env.step(action_n)
  • We call
    in what looks like a busy loop. In reality, there is a
    __ wrapper on the client which defaults to a target frame rate of 60fps, or one frame every 16.7ms. If you call it more frequently than that,
    __ with any leftover time.


We are using

__ for tests. You can run them via:

.. code:: shell



pytest --help
for useful options, such as
pytest -s
(disables output capture) or
pytest -k 
(runs only specific tests).

Additional documentation

More documentation not covered in this README can be found in the

doc folder 
__ of this repository.

Getting help

If you encounter a problem that is not addressed in this README page or in the

extra docs 
, then try our wiki page of
to common problems
- and add to it if your solution isn't there!

You can also search through the

__ on this repository and our
discussion board
__ to see if another user has posted about the same problem or to ask for help from the community.

If you still can't solve your problem after trying all of the above steps, please post an issue on this repository.

What's next?

  • Get started training RL algorithms! You can try out the

    Universe Starter Agent 
    , an implementation of the
    A3C algorithm 
    that can solve several VNC environments.
  • For more information on how to manage remotes, see the separate documentation page on

  • Sign up for a

    _ to get early access to upcoming Universe releases, such as tools to integrate new Universe environments or a dataset of recorded human demonstrations.


  • 2017-02-08: The old location for wrappers.SafeActionSpace has been moved to wrappers.experimental.SafeActionSpace. SoftmaxClickMouse has also been moved to wrappers.experimental.SoftmaxClickMouse
  • 2017-01-08: The wrappers.SafeActionSpace has been moved to wrappers.experimental.SafeActionSpace. The old location will remain with a deprecation warning until 2017-02-08.
  • 2016-12-27: BACKWARDS INCOMPATIBILITY: The gym monitor is now a wrapper. Rather than starting monitoring as
    , envs are now wrapped as follows:
    env = wrappers.Monitor(env, directory)
    . This change is on master and will be released with 0.21.0.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.