Counting 2,772 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1


License Docs DOI


Coach is a python reinforcement learning research framework containing implementation of many state-of-the-art algorithms.

It exposes a set of easy-to-use APIs for experimenting with new RL algorithms, and allows simple integration of new environments to solve. Basic RL components (algorithms, environments, neural network architectures, exploration policies, ...) are well decoupled, so that extending and reusing existing components is fairly painless.

Training an agent to solve an environment is as easy as running:

python3 -p CartPole_DQN -r

Doom Deathmatch CARLA MontezumaRevenge

Blog posts from the Intel® AI website:

Contacting the Coach development team is also possible through the email [email protected]

Table of Contents


Framework documentation, algorithm description and instructions on how to contribute a new agent/environment can be found here.


Note: Coach has only been tested on Ubuntu 16.04 LTS, and with Python 3.5.

Coach Installer

Coach's installer will setup all the basics needed to get the user going with running Coach on top of OpenAI Gym environments. This can be done by running the following command and then following the on-screen printed instructions:


Coach creates a virtual environment and installs in it to avoid changes to the user's system.

In order to activate and deactivate Coach's virtual environment:

source coach_env/bin/activate

In addition to OpenAI Gym, several other environments were tested and are supported. Please follow the instructions in the Supported Environments section below in order to install more environments.

TensorFlow GPU Support

Coach's installer installs Intel-Optimized TensorFlow, which does not support GPU, by default. In order to have Coach running with GPU, a GPU supported TensorFlow version must be installed. This can be done by overriding the TensorFlow version:

pip3 install tensorflow-gpu


Running Coach

Coach supports both TensorFlow and neon deep learning frameworks.

Switching between TensorFlow and neon backends is possible by using the -f flag.

Using TensorFlow (default): -f tensorflow

Using neon: -f neon

There are several available presets in To list all the available presets use the -l flag.

To run a preset, use:

python3 -r -p <preset_name>

For example:

  1. CartPole environment using Policy Gradients:
python3 -r -p CartPole_PG
  1. Pendulum using Clipped PPO:
python3 -r -p Pendulum_ClippedPPO -n 8
  1. MountainCar using A3C:
python3 -r -p MountainCar_A3C -n 8
  1. Doom basic level using Dueling network and Double DQN algorithm:
 python3 -r -p Doom_Basic_Dueling_DDQN
  1. Doom health gathering level using Mixed Monte Carlo:
python3 -r -p Doom_Health_MMC

It is easy to create new presets for different levels or environments by following the same pattern as in

More usage examples can be found here.

Running Coach Dashboard (Visualization)

Training an agent to solve an environment can be tricky, at times.

In order to debug the training process, Coach outputs several signals, per trained algorithm, in order to track algorithmic performance.

While Coach trains an agent, a csv file containing the relevant training signals will be saved to the 'experiments' directory. Coach's dashboard can then be used to dynamically visualize the training signals, and track algorithmic behavior.

To use it, run:


Coach Design

Parallelizing an Algorithm

Since the introduction of A3C in 2016, many algorithms were shown to benefit from running multiple instances in parallel, on many CPU cores. So far, these algorithms include A3C, DDPG, PPO, and NAF, and this is most probably only the begining.

Parallelizing an algorithm using Coach is straight-forward.

The following method of NetworkWrapper parallelizes an algorithm seamlessly:

network.train_and_sync_networks(current_states, targets)

Once a parallelized run is started, the train_and_sync_networks API will apply gradients from each local worker's network to the main global network, allowing for parallel training to take place.

Then, it merely requires running Coach with the -n flag and with the number of workers to run with. For instance, the following command will set 16 workers to work together to train a MuJoCo Hopper:

python3 -p Hopper_A3C -n 16

Supported Environments

  • OpenAI Gym:

    Installed by default by Coach's installer.

  • ViZDoom:

    Follow the instructions described in the ViZDoom repository -

    Additionally, Coach assumes that the environment variable VIZDOOM_ROOT points to the ViZDoom installation directory.

  • Roboschool:

    Follow the instructions described in the roboschool repository -

  • GymExtensions:

    Follow the instructions described in the GymExtensions repository -

    Additionally, add the installation directory to the PYTHONPATH environment variable.

  • PyBullet:

    Follow the instructions described in the Quick Start Guide (basically just - 'pip install pybullet')

  • CARLA:

    Download release 0.7 from the CARLA repository -

    Create a new CARLA_ROOT environment variable pointing to CARLA's installation directory.

    A simple CARLA settings file (CarlaSettings.ini) is supplied with Coach, and is located in the environments directory.

Supported Algorithms

Coach Design


If you used Coach for your work, please use the following citation:

  author       = {Caspi, Itai and
                  Leibovich, Gal and
                  Novik, Gal},
  title        = {Reinforcement Learning Coach},
  month        = dec,
  year         = 2017,
  doi          = {10.5281/zenodo.1134899},
  url          = {}


Coach is released as a reference code for research purposes. It is not an official Intel product, and the level of quality and support may not be as expected from an official product. Additional algorithms and environments are planned to be added to the framework. Feedback and contributions from the open source and RL research communities are more than welcome.

Latest Releases
Release 0.9
 Dec. 19 2017
 Oct. 19 2017