Project details for PILCO policy search framework

Logo PILCO policy search framework 0.9

by marc - September 27, 2013, 12:45:12 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ]

view (2 today), download ( 1 today ), 1 comment, 0 subscriptions


This software package allows the user to easily apply the powerful pilco framework to a wide range of continuous-valued RL and control problems, requiring only a small amount of problem-specific extra coding. The package includes five example scenarios as demonstrations of what is possible and to help the user apply the package to their own problems. The high-level steps of the pilco algorithm are the following: Learn a Gaussian process (GP) model of the system dynamics, perform deterministic approximate inference for policy evaluation, update the policy parameters using exact gradient information, apply the learned controller to the system. The software package provides an interface, which allows for setting up novel tasks without the need to be familiar with the intricate details of model learning, policy evaluation and improvement.

Changes to previous version:

Initial Announcement on

BibTeX Entry: Download
Corresponding Paper BibTeX Entry: Download
Supported Operating Systems: Agnostic
Data Formats: Agnostic
Tags: Control, Reinforcement Learning, Approximate Inference, Gaussian Processes, Policy Search
Archive: download here


Marc Deisenroth (on October 1, 2013, 15:48:14)
added thumbnail

Leave a comment

You must be logged in to post comments.