Skip to main content

A framework for learning about and experimenting with reinforcement learning algorithms

Project description


.. image::

.. image::

.. image::
:alt: Documentation Status

.. image::
:alt: Updates

A framework for learning about and experimenting with reinforcement learning algorithms.
It is built on top of TensorFlow and `TFLearn <>`_ and is interfaces
with the OpenAI gym (universe should work, too). It aims to be as modular as possible so
that new algorithms and ideas can easily be tested. I started it to gain a better
understanding of core RL algorithms and maybe it can be useful for others as well.


Algorithms (future algorithms italicized):

- MDP algorithms

+ Value iteration
+ Policy iteration

- Temporal Difference Learning

+ Deep Q-Learning
+ *Policy gradient Q-learning*

- Gradient algorithms

+ Vanilla policy gradient
+ *Deterministic policy gradient*
+ *Natural policy gradient*

- Gradient-Free algorithms

+ *Cross entropy method*

Function approximators (defined by TFLearn model):

- Linear
- Neural network
- *RBF*

Works with any OpenAI gym environment.

Future Enhancements

* Improved TensorBoard logging
* Improved model snapshotting to include exploration states, memories, etc.
* Any suggestions?

* Errors / warnings on TensorFlow session save


* Free software: MIT license
* Documentation:


0.1.2/3 (2016-17-15)

* Improving meta data and fixing __init__ scripts to load subpackages properly

0.1.0 (2016-16-15)

* First release on PyPI.

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

rlflow-0.1.3.tar.gz (27.0 kB view hashes)

Uploaded source

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