linesd / PILCO

Bayesian Reinforcement Learning in Tensorflow

Probabilistic Inference for Learning Control

A modern & clean implementation of the PILCO Algorithm in TensorFlow.

Unlike PILCO's original implementation which was written as a self-contained package of MATLAB, this repository aims to provide a clean implementation by heavy use of modern machine learning libraries.

In particular, we use TensorFlow to avoid the need for hardcoded gradients and scale to GPU architectures. Moreover, we use GPflow for Gaussian Process Regression.

The core functionality is tested against the original MATLAB implementation.

Example of usage

First install the package by running:

python setup.py develop

Then you can run the example of using PILCO in OpenAI gym by running

python examples/inverted_pendulum.py

Credits:

The following people have been involved in the development of this package:

• Nikitas Rontsis
• Kyriakos Polymenakos

References

See the following publications for a description of the algorithm: 1, 2, 3