Initial release. Hello world :).

.gitignore

@@ -0,0 +1,31 @@
+*.swp
+*.pyc
+*.py~
+.DS_Store
+
+# Setuptools distribution and build folders.
+/dist/
+/build
+
+# Virtualenv
+/env
+
+# Python egg metadata, regenerated from source files by setuptools.
+/*.egg-info
+
+*.sublime-project
+*.sublime-workspace
+
+logs/
+
+.ipynb_checkpoints
+ghostdriver.log
+
+junk
+MUJOCO_LOG.txt
+mujoco-bundle
+
+
+rllab_mujoco
+
+tutorial/*.html

.travis.yml

@@ -0,0 +1,32 @@
+dist: trusty
+sudo: required
+cache:
+  apt: true
+  pip: false
+language: python
+python:
+  - "2.7"
+  # - "3.2"
+
+# Install numpy and scipy so we don't need to compile them
+addons:
+    apt:
+      packages:
+        - python-numpy
+        - python-matplotlib
+        - python-tk
+
+before_install:
+  - Xvfb :12 -screen 0 800x600x24 +extension RANDR &
+  - mkdir -p ~/.mujoco
+  - curl https://openai-public.s3-us-west-2.amazonaws.com/mujoco/$MUJOCO_KEY_BUNDLE.tar.gz | tar xz -C ~/.mujoco
+env:
+  - DISPLAY=:12
+
+install: pip install -r requirements.txt
+script: nose2
+
+notifications:
+  slack:
+    secure: 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
+    on_success: change

CODE_OF_CONDUCT.rst

@@ -0,0 +1,13 @@
+OpenAI Gym is dedicated to providing a harassment-free experience for
+everyone, regardless of gender, gender identity and expression, sexual
+orientation, disability, physical appearance, body size, age, race, or
+religion. We do not tolerate harassment of participants in any form.
+
+This code of conduct applies to all OpenAI Gym spaces (including Gist
+comments) both online and off. Anyone who violates this code of
+conduct may be sanctioned or expelled from these spaces at the
+discretion of the OpenAI team.
+
+We may add additional rules over time, which will be made clearly
+available to participants. Participants are responsible for knowing
+and abiding by these rules.

Dockerfile

@@ -0,0 +1,35 @@
+# A Dockerfile that sets up a full Gym install
+FROM ubuntu:14.04
+
+RUN apt-get update \
+    && apt-get install -y xorg-dev \
+    libgl1-mesa-dev \
+    xvfb \
+    libxinerama1 \
+    libxcursor1 \
+    libglu1-mesa \
+    libav-tools \
+    python-numpy \
+    python-scipy \
+    python-pyglet \
+    python-setuptools \
+    libpq-dev \
+    libjpeg-dev \
+    curl \
+    cmake \
+ && apt-get clean \
+ && rm -rf /var/lib/apt/lists/* \
+ && easy_install pip
+
+WORKDIR /usr/local/gym
+RUN mkdir gym && touch gym/__init__.py
+COPY ./gym/version.py ./gym
+COPY ./requirements.txt .
+COPY ./setup.py .
+RUN pip install -r requirements.txt
+
+# Finally, upload our actual code!
+COPY . /usr/local/gym
+
+WORKDIR /root
+ENTRYPOINT ["/usr/local/gym/bin/docker_entrypoint"]

Makefile

@@ -0,0 +1,7 @@
+.PHONY: install test
+
+install:
+	pip install -r requirements.txt
+
+test:
+	nose2

README.rst

@@ -0,0 +1,208 @@
+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 an ever-growing variety of environments.
+
+``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 <https://gym.openai.com/docs>`_ on our site.
+
+.. contents:: **Contents of this document**
+   :depth: 2
+
+Basics
+======
+
+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
+<https://github.com/openai/gym/blob/master/gym/core.py>`_, 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`, `action`, `reward`, `done`.
+- `render(self, mode='human', close=False)`: Render one frame of the environment. The default mode will do something human friendly, such as pop up a window. Passing the `close` flag signals the renderer to close any such windows.
+
+Installation
+============
+
+You can perform a minimal install of ``gym`` with:
+
+.. code:: shell
+	  
+	  git clone [email protected]:gym
+	  cd gym
+	  pip install -e .
+
+You'll be able to run a few environments right away:
+
+- `algorithmic <https://gym.openai.com/envs#algorithmic>`_
+- `toy_text <https://gym.openai.com/envs#toy_text>`_
+- `classic_control <https://gym.openai.com/envs#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
+---------------------
+
+Once you're ready to install everything, run ``pip install -e .[all]``.
+
+MuJoCo has a proprietary dependency we can't set up for you. Follow
+the
+`instructions <https://github.com/openai/mujoco-py#obtaining-the-binaries-and-license-key>`_
+in the ``mujoco-py`` package for help.
+
+For the install to succeed, 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.
+
+On Ubuntu 14.04:
+
+.. code:: shell
+	  
+	  apt-get install -y numpy python-dev cmake zlib1g-dev libjpeg-dev xvfb libav-tools xorg-dev python-opengl
+
+Supported systems
+-----------------
+
+We currenty support Python 2.7 on Linux and OSX.
+
+We will expand support to Python 3 and Windows based on demand. We
+will also soon ship a Docker container exposing OpenAI Gym as an API
+callable from any platform.
+
+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 `setup.py
+<https://github.com/openai/gym/blob/master/setup.py>`_ and
+install the dependencies by hand.
+
+Installing dependencies for specific environments
+-------------------------------------------------
+
+If you'd like to install the dependencies for only specific
+environments, see `setup.py
+<https://github.com/openai/gym/blob/master/setup.py>`_. We
+maintain the lists of dependencies on a per-environment group basis.
+
+Environments
+============
+
+The code for each environment group is housed in its own subdirectory
+`gym/envs
+<https://github.com/openai/gym/blob/master/gym/envs>`_. The
+specification of each task is in `gym/envs/__init__.py
+<https://github.com/openai/gym/blob/master/gym/envs/__init__.py>`_. It's
+worth browsing through both.
+
+Algorithmic
+-----------
+
+These are a variety of algorithmic tasks, such as learning to copy a
+sequence.
+
+.. code:: python
+
+	  import gym
+	  env = gym.make('Copy-v0')
+	  env.reset()
+	  env.render()
+
+Atari
+-----
+
+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]`` and then get started as follow:
+
+.. code:: python
+
+	  import gym
+	  env = gym.make('SpaceInvaders-v0')
+	  env.reset()
+	  env.render()
+
+This will install ``atari-py``, which automatically compiles the `Arcade Learning Environment <http://www.arcadelearningenvironment.org/>`_. This can take quite a while (a few minutes on a decent laptop), so just be prepared.
+
+Board games
+-----------
+
+The board game environments are a variety of board games. If you didn't do the full install, you can install dependencies via ``pip install -e .[board_game]`` and then get started as follow:
+
+.. code:: python
+
+	  import gym
+	  env = gym.make('Go9x9-v0')
+	  env.reset()
+	  env.render()
+
+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:
+
+.. code:: python
+
+	  import gym
+	  env = gym.make('CartPole-v0')
+	  env.reset()
+	  env.render()
+
+MuJoCo
+------
+
+`MuJoCo <http://www.mujoco.org/>`_ 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
+<https://github.com/openai/mujoco-py#obtaining-the-binaries-and-license-key>`_
+to set it up. You'll have to also run ``pip install -e .[mujoco]`` if you didn't do the full install.
+
+.. code:: python
+
+	  import gym
+	  env = gym.make('Humanoid')
+	  env.reset()
+	  env.render()
+
+Toy text
+--------
+
+Toy environments which are text-based. There's no extra dependency to install, so to get started, you can just do:
+
+.. code:: python
+
+	  import gym
+	  env = gym.make('FrozenLake')
+	  env.reset()
+	  env.render()
+
+Examples
+========
+
+See the ``examples`` directory.
+
+- Run `examples/agents/random_agent.py <https://github.com/openai/gym/blob/master/examples/agents/random_agent.py>`_ to run an simple random agent and upload the results to the scoreboard.
+- Run `examples/agents/cem.py <https://github.com/openai/gym/blob/master/examples/agents/cem.py>`_ to run an actual learning agent (using the cross-entropy method) and upload the results to the scoreboard.
+- Run `examples/scripts/list_envs <https://github.com/openai/gym/blob/master/examples/scripts/list_envs>`_ to generate a list of all environments. (You see also just `browse <https://gym.openai.com/docs>`_ the list on our site.
+  - Run `examples/scripts/upload <https://github.com/openai/gym/blob/master/examples/scripts/upload>`_ to upload the recorded output from ``random_agent.py`` or ``cem.py``. Make sure to obtain an `API key <https://gym.openai.com/settings/profile>`_.
+
+Testing
+=======
+
+We are using `nose2 <https://github.com/nose-devs/nose2>`_ for tests. You can run them via
+
+.. code:: shell
+
+	  nose2
+
+You can also run tests in a specific directory by using the ``-s`` option, or by passing in the specific name of the test. See the `nose2 docs <http://nose2.readthedocs.org/en/latest/usage.html#naming-tests>`_ for more details.

bin/docker_entrypoint

@@ -0,0 +1,12 @@
+#!/bin/sh
+
+# This script is the entrypoint for our Docker image.
+
+set -e
+
+# Set up display; otherwise rendering will cause segfaults
+rm -f /tmp/.X12-lock
+Xvfb :12 -screen 0 800x600x24 +extension RANDR 2>/dev/null &
+export DISPLAY=:12
+
+exec "$@"

examples/agents/_policies.py

@@ -0,0 +1,19 @@
+# Support code for cem.py
+
+class BinaryActionLinearPolicy(object):
+    def __init__(self, theta):
+        self.w = theta[:-1]
+        self.b = theta[-1]
+    def act(self, ob):
+        y = ob.dot(self.w) + self.b
+        a = int(y < 0)
+        return a
+
+class ContinuousActionLinearPolicy(object):
+    def __init__(self, theta, n_in, n_out):
+        assert len(theta) == (n_in + 1) * n_out
+        self.W = theta[0 : n_in * n_out].reshape(n_in, n_out)
+        self.b = theta[n_in * n_out : None].reshape(1, n_out)
+    def act(self, ob):
+        a = ob.dot(self.W) + self.b
+        return a