Michigan-style Learning Classifier Systems
Project description
Piecewise
What is Piecewise?
A Michigan-style Learning Classifier System (LCS) library, written in Python.
It makes heavy use of object-oriented language features to provide a modular, extensible framework on which to build LCS algorithms.
The currently implemented algorithms are:
- XCS (ternary rule representation)
- XCSR (centre-spread rule representation)
Project Philosophy
The primary use case of Piecewise is for LCS researchers who are interested in:
- Investigating modifications or extensions to existing LCS algorithms.
- Running experiments with LCS algorithms on common environments, through a standardised and easy-to-use interface.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
piecewise-0.1.tar.gz
(1.4 kB
view hashes)