Skip to content

Latest commit

 

History

History
14 lines (10 loc) · 528 Bytes

DESCRIPTION.rst

File metadata and controls

14 lines (10 loc) · 528 Bytes

LSPI Python

This is a Python implementation of the Least Squares Policy Iteration (LSPI) reinforcement learning algorithm. For more information on the algorithm please refer to the paper

“Least-Squares Policy Iteration.”
Lagoudakis, Michail G., and Ronald Parr.
Journal of Machine Learning Research 4, 2003.

You can also visit their website where more information and a Matlab version is provided.

http://www.cs.duke.edu/research/AI/LSPI/