Skip to main content

Framework for deep reinforcement learning

Project description

Travis Python27 Python35 PyPi License

DeeR

DeeR is a python library for Deep Reinforcement. It is build with modularity in mind so that it can easily be adapted to any need. It provides many possibilities out of the box (prioritized experience replay, double Q-learning, DDPG, etc). Many different environment examples are also provided (some of them using OpenAI gym).

Dependencies

This framework is tested to work under Python 2.7, and Python 3.5. It should also work with Python 3.3 and 3.4.

The required dependencies are NumPy >= 1.10, joblib >= 0.9. You also need theano >= 0.8 or tensorflow >= 0.9 along with the keras library.

For running the examples, Matplotlib >= 1.1.1 is required. For running the atari games environment, you need to install ALE >= 0.4.

Full Documentation

The documentation is available at : http://deer.readthedocs.io/

Here are a few examples :

http://vincent.francois-l.be/img_GeneralDeepQRL/seaquest.gif http://vincent.francois-l.be/img_GeneralDeepQRL/output7.gif

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

deer-0.3.1.tar.gz (64.9 kB view hashes)

Uploaded Source

Built Distribution

deer-0.3.1-py2-none-any.whl (166.7 kB view hashes)

Uploaded Python 2

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page