Deobfuscation of the code base + pep8 and fixes

.coveragerc

@@ -0,0 +1,15 @@
+[run]
+branch = False
+omit =
+    # Mujoco requires a licence
+    stable_baselines/*/run_mujoco.py
+    stable_baselines/ppo1/run_humanoid.py
+    stable_baselines/ppo1/run_robotics.py
+    # HER requires mpi and Mujoco
+    stable_baselines/her/experiment/
+
+[report]
+exclude_lines =
+    pragma: no cover
+    raise NotImplementedError()
+    if KFAC_DEBUG:

.gitignore

@@ -2,9 +2,14 @@
 *.pyc
 *.pkl
 *.py~
+*.bak
 .pytest_cache
 .DS_Store
 .idea
+.coverage
+.coverage.*
+__pycache__/
+_build/
 
 # Setuptools distribution and build folders.
 /dist/
@@ -34,5 +39,3 @@ src
 .cache
 
 MUJOCO_LOG.TXT
-
-

.travis.yml

@@ -2,6 +2,9 @@ language: python
 python:
     - "3.6"
 
+notifications:
+    email: false
+
 services:
     - docker
 
@@ -10,5 +13,5 @@ install:
     - docker build . -t baselines-test
 
 script:
-    - flake8 --select=F baselines/common
-    - docker run baselines-test pytest
+    - flake8 --select=F stable_baselines/common
+    - docker run --env CODACY_PROJECT_TOKEN=$CODACY_PROJECT_TOKEN baselines-test sh -c 'pytest --cov-config .coveragerc --cov-report term --cov-report xml --cov=. && python-codacy-coverage -r coverage.xml --token=$CODACY_PROJECT_TOKEN'

Dockerfile

@@ -1,20 +1,45 @@
 FROM ubuntu:16.04
 
-RUN apt-get -y update && apt-get -y install git wget python-dev python3-dev libopenmpi-dev python-pip zlib1g-dev cmake
+RUN apt-get -y update && apt-get -y install git wget python-dev python3-dev libopenmpi-dev python-pip zlib1g-dev cmake libglib2.0-0 libsm6 libxext6 libfontconfig1 libxrender1
 ENV CODE_DIR /root/code
 ENV VENV /root/venv
 
-COPY . $CODE_DIR/baselines
 RUN \
     pip install virtualenv && \
     virtualenv $VENV --python=python3 && \
     . $VENV/bin/activate && \
+    mkdir $CODE_DIR && \
     cd $CODE_DIR && \
     pip install --upgrade pip && \
-    pip install -e baselines && \
-    pip install pytest
+    pip install pytest && \
+    pip install pytest-cov && \
+    pip install codacy-coverage && \
+    pip install scipy && \
+    pip install tqdm && \
+    pip install joblib && \
+    pip install zmq && \
+    pip install dill && \
+    pip install progressbar2 && \
+    pip install mpi4py && \
+    pip install cloudpickle && \
+    pip install tensorflow>=1.5.0 && \
+    pip install click && \
+    pip install opencv-python && \
+    pip install numpy && \
+    pip install pandas && \
+    pip install pytest && \
+    pip install matplotlib && \
+    pip install seaborn && \
+    pip install glob2 && \
+    pip install gym[mujoco,atari,classic_control,robotics]
+
+COPY . $CODE_DIR/stable_baselines
+RUN \
+    . $VENV/bin/activate && \
+    cd $CODE_DIR && \
+    pip install -e stable_baselines
 
 ENV PATH=$VENV/bin:$PATH
-WORKDIR $CODE_DIR/baselines
+WORKDIR $CODE_DIR/stable_baselines
 
 CMD /bin/bash

README.md

@@ -1,87 +1,163 @@
-<img src="data/logo.jpg" width=25% align="right" /> [![Build status](https://travis-ci.org/openai/baselines.svg?branch=master)](https://travis-ci.org/openai/baselines)
+[![Build Status](https://travis-ci.com/hill-a/stable-baselines.svg?branch=stable)](https://travis-ci.com/hill-a/stable-baselines) [![Documentation Status](https://readthedocs.org/projects/stable-baselines/badge/?version=docs)](https://stable-baselines.readthedocs.io/en/docs/?badge=master) [![Codacy Badge](https://api.codacy.com/project/badge/Grade/3bcb4cd6d76a4270acb16b5fe6dd9efa)](https://www.codacy.com/app/baselines_janitors/stable-baselines?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=hill-a/stable-baselines&amp;utm_campaign=Badge_Grade) [![Codacy Badge](https://api.codacy.com/project/badge/Coverage/3bcb4cd6d76a4270acb16b5fe6dd9efa)](https://www.codacy.com/app/baselines_janitors/stable-baselines?utm_source=github.com&utm_medium=referral&utm_content=hill-a/stable-baselines&utm_campaign=Badge_Coverage)
 
-# Baselines
+# Stable Baselines
 
-OpenAI Baselines is a set of high-quality implementations of reinforcement learning algorithms.
+Stable Baselines is a set of improved implementations of reinforcement learning algorithms based on OpenAI [Baselines](https://github.com/openai/baselines/).
 
-These algorithms will make it easier for the research community to replicate, refine, and identify new ideas, and will create good baselines to build research on top of. Our DQN implementation and its variants are roughly on par with the scores in published papers. We expect they will be used as a base around which new ideas can be added, and as a tool for comparing a new approach against existing ones. 
+You can read a detailed presentation of Stable Baselines in the [Medium article](https://medium.com/@araffin/stable-baselines-a-fork-of-openai-baselines-reinforcement-learning-made-easy-df87c4b2fc82).
 
-## Prerequisites 
+
+These algorithms will make it easier for the research community and industry to replicate, refine, and identify new ideas, and will create good baselines to build projects on top of. We expect these tools will be used as a base around which new ideas can be added, and as a tool for comparing a new approach against existing ones. We also hope that the simplicity of these tools will allow beginners to experiment with a more advanced toolset, without being buried in implementation details.
+
+## Main differences with OpenAI Baselines
+
+This toolset is a fork of OpenAI Baselines, with a major structural refactoring, and code cleanups:
+- Unified structure for all algorithms
+- PEP8 compliant (unified code style)
+- Documented functions and classes
+- More tests & more code coverage
+
+## Documentation
+
+Documentation is available online: [http://stable-baselines.readthedocs.io/](http://stable-baselines.readthedocs.io/)
+
+## Installation
+
+### Prerequisites
 Baselines requires python3 (>=3.5) with the development headers. You'll also need system packages CMake, OpenMPI and zlib. Those can be installed as follows
-### Ubuntu 
-
+
+#### Ubuntu
+
 ```bash
 sudo apt-get update && sudo apt-get install cmake libopenmpi-dev python3-dev zlib1g-dev
 ```
-    
-### Mac OS X
+
+#### Mac OS X
 Installation of system packages on Mac requires [Homebrew](https://brew.sh). With Homebrew installed, run the follwing:
 ```bash
 brew install cmake openmpi
 ```
-
-## Virtual environment
-From the general python package sanity perspective, it is a good idea to use virtual environments (virtualenvs) to make sure packages from different projects do not interfere with each other. You can install virtualenv (which is itself a pip package) via
-```bash
-pip install virtualenv
-```
-Virtualenvs are essentially folders that have copies of python executable and all python packages.
-To create a virtualenv called venv with python3, one runs 
-```bash
-virtualenv /path/to/venv --python=python3
-```
-To activate a virtualenv: 
+
+### Install using pip
+Install the Stable Baselines package
+
+Using pip from pypi:
 ```
-. /path/to/venv/bin/activate
+pip install stable-baselines
 ```
-More thorough tutorial on virtualenvs and options can be found [here](https://virtualenv.pypa.io/en/stable/) 
 
+Please read the [documentation](http://stable-baselines.readthedocs.io/) for more details and alternatives.
 
-## Installation
-Clone the repo and cd into it:
-```bash
-git clone https://github.com/openai/baselines.git
-cd baselines
-```
-If using virtualenv, create a new virtualenv and activate it
-```bash
-    virtualenv env --python=python3
-    . env/bin/activate
+
+## Example
+
+Most of the library tries to follow a sklearn-like syntax for the Reinforcement Learning algorithms.
+
+Here is a quick example of how to train and run PPO2 on a cartpole environment:
+```python
+import gym
+
+from stable_baselines.common.policies import MlpPolicy
+from stable_baselines.common.vec_env import DummyVecEnv
+from stable_baselines import PPO2
+
+env = gym.make('CartPole-v1')
+env = DummyVecEnv([lambda: env])  # The algorithms require a vectorized environment to run
+
+model = PPO2(MlpPolicy, env, verbose=1)
+model.learn(total_timesteps=10000)
+
+obs = env.reset()
+for i in range(1000):
+    action, _states = model.predict(obs)
+    obs, rewards, dones, info = env.step(action)
+    env.render()
 ```
-Install baselines package
-```bash
-pip install -e .
+
+Or just train a model with a one liner if [the environment is registed in Gym](https://github.com/openai/gym/wiki/Environments):
+
+```python
+
+from stable_baselines.common.policies import MlpPolicy
+from stable_baselines import PPO2
+
+model = PPO2(MlpPolicy, 'CartPole-v1').learn(10000)
+
 ```
-### MuJoCo
+
+Please read the [documentation](http://stable-baselines.readthedocs.io/) for more examples.
+
+
+## Try it online with Colab Notebooks !
+
+All the following examples can be executed online using Google colab notebooks:
+
+- [Getting Started](https://colab.research.google.com/drive/1_1H5bjWKYBVKbbs-Kj83dsfuZieDNcFU)
+- [Training, Saving, Loading](https://colab.research.google.com/drive/1KoAQ1C_BNtGV3sVvZCnNZaER9rstmy0s)
+- [Multiprocessing](https://colab.research.google.com/drive/1ZzNFMUUi923foaVsYb4YjPy4mjKtnOxb)
+- [Monitor Training and Plotting](https://colab.research.google.com/drive/1L_IMo6v0a0ALK8nefZm6PqPSy0vZIWBT)
+- [Atari Games](https://colab.research.google.com/drive/1iYK11yDzOOqnrXi1Sfjm1iekZr4cxLaN)
+
+
+## Implemented Algorithms
+
+| **Name**            | **Refactored**<sup>(1)</sup> | **Recurrent**      | ```Box```          | ```Discrete```     | ```MultiDiscrete``` | ```MultiBinary```  | **Multi Processing**              |
+| ------------------- | ---------------------------- | ------------------ | ------------------ | ------------------ | ------------------- | ------------------ | --------------------------------- |
+| A2C                 | :heavy_check_mark:           | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark:  | :heavy_check_mark: | :heavy_check_mark:                |
+| ACER                | :heavy_check_mark:           | :heavy_check_mark: | :x: <sup>(5)</sup> | :heavy_check_mark: | :x:                 | :x:                | :heavy_check_mark:                |
+| ACKTR               | :heavy_check_mark:           | :heavy_check_mark: | :x: <sup>(5)</sup> | :heavy_check_mark: | :x:                 | :x:                | :heavy_check_mark:                |
+| DDPG                | :heavy_check_mark:           | :x:                | :heavy_check_mark: | :x:                | :x:                 | :x:                | :x:                               |
+| DeepQ               | :heavy_check_mark:           | :x:                | :x:                | :heavy_check_mark: | :x:                 | :x:                | :x:                               |
+| GAIL <sup>(2)</sup> | :heavy_check_mark:           | :heavy_check_mark: | :heavy_check_mark: | :x:                | :x:                 | :x:                | :heavy_check_mark: <sup>(4)</sup> |
+| HER <sup>(3)</sup>  | :x: <sup>(5)</sup>           | :x:                | :heavy_check_mark: | :x:                | :x:                 | :x:                | :x:                               |
+| PPO1                | :heavy_check_mark:           | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark:  | :heavy_check_mark: | :heavy_check_mark: <sup>(4)</sup> |
+| PPO2                | :heavy_check_mark:           | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark:  | :heavy_check_mark: | :heavy_check_mark:                |
+| TRPO                | :heavy_check_mark:           | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark:  | :heavy_check_mark: | :heavy_check_mark: <sup>(4)</sup> |
+
+<sup><sup>(1): Whether or not the algorithm has be refactored to fit the ```BaseRLModel``` class.</sup></sup><br>
+<sup><sup>(2): Only implemented for TRPO.</sup></sup><br>
+<sup><sup>(3): Only implemented for DDPG.</sup></sup><br>
+<sup><sup>(4): Multi Processing with [MPI](https://mpi4py.readthedocs.io/en/stable/).</sup></sup><br>
+<sup><sup>(5): TODO, in project scope.</sup></sup>
+
+Actions ```gym.spaces```:
+ * ```Box```: A N-dimensional box that containes every point in the action space.
+ * ```Discrete```: A list of possible actions, where each timestep only one of the actions can be used.
+ * ```MultiDiscrete```: A list of possible actions, where each timestep only one action of each discrete set can be used.
+ * ```MultiBinary```: A list of possible actions, where each timestep any of the actions can be used in any combination.
+
+
+## MuJoCo
 Some of the baselines examples use [MuJoCo](http://www.mujoco.org) (multi-joint dynamics in contact) physics simulator, which is proprietary and requires binaries and a license (temporary 30-day license can be obtained from [www.mujoco.org](http://www.mujoco.org)). Instructions on setting up MuJoCo can be found [here](https://github.com/openai/mujoco-py)
 
 ## Testing the installation
 All unit tests in baselines can be run using pytest runner:
 ```
-pip install pytest
-pytest
+pip install pytest pytest-cov
+pytest --cov-config .coveragerc --cov-report html --cov-report term --cov=.
 ```
 
-## Subpackages
-
-- [A2C](baselines/a2c)
-- [ACER](baselines/acer)
-- [ACKTR](baselines/acktr)
-- [DDPG](baselines/ddpg)
-- [DQN](baselines/deepq)
-- [GAIL](baselines/gail)
-- [HER](baselines/her)
-- [PPO1](baselines/ppo1) (Multi-CPU using MPI)
-- [PPO2](baselines/ppo2) (Optimized for GPU)
-- [TRPO](baselines/trpo_mpi)
+## Citing the Project
 
 To cite this repository in publications:
 
-    @misc{baselines,
-      author = {Dhariwal, Prafulla and Hesse, Christopher and Klimov, Oleg and Nichol, Alex and Plappert, Matthias and Radford, Alec and Schulman, John and Sidor, Szymon and Wu, Yuhuai},
-      title = {OpenAI Baselines},
-      year = {2017},
+```
+    @misc{stable-baselines,
+      author = {Hill, Ashley and Raffin, Antonin and Traore, Rene and Dhariwal, Prafulla and Hesse, Christopher and Klimov, Oleg and Nichol, Alex and Plappert, Matthias and Radford, Alec and Schulman, John and Sidor, Szymon and Wu, Yuhuai},
+      title = {Stable Baselines},
+      year = {2018},
       publisher = {GitHub},
       journal = {GitHub repository},
-      howpublished = {\url{https://github.com/openai/baselines}},
+      howpublished = {\url{https://github.com/hill-a/stable-baselines}},
     }
+```
+
+## How To Contribute
+
+To any interested in making the baselines better, there is still some documentation that needs to be done.
+If you want to contribute, please open an issue first and then propose your pull request.
+
+Nice to have (for the future):
+- [ ] Continuous actions support for ACER
+- [ ] Continuous actions support for ACKTR
+- [ ] Tensorboard integration (see branch `Tensorboard`)