pftq.com

QLearner

QLearner

Date: July 22, 2013

Released: Jul 22, 2013, last updated Jul 18, 2015

Type: Web|Script|Tool

Download/View: QLearner

Downloads/Hits: 266

Version: 1-3

Tags/Keywords: AI, Q-Learning, Machine Learning, CSharp

Description:





- Start QLearner -
- Download QLearner Plugins Template -
- Help and Discussion -
Also available open-source on Github.com

Note: Application requires Windows, .NET 4, and either Internet Explorer, .NET for Firefox, or .NET for Chrome.

"A practical, generalized application of various machine learning algorithms for C# programming."


QLearner provides generalized machine learning algorithms to solve to any problem defined by a QState.  The Plugins Template download includes a template to build your own QStates and several examples to learn from.  For more advanced users, new QAlgos can also be created to leverage the framework provided by QLearner.  Documentation and API are provided for developing your own plugins, so that it is not necessary to actually modify the source code of the underlying QLearner framework.  Additionally, QLearner can be compiled or included as a class library for instantiating instances of QLearner's algos for your own code projects.

To use QLearner, simply open the QLearner program and click on the QState box to select a problem to solve and the QAlgo box to choose an algorithm to solve it with.  Press Learn to give QLearner a chance to "practice" at the problem and learn about it.  Press Awaken for QLearner to apply its most current knowledge to solve the problem in the most efficient way it currently knows how.  To use QLearner programatically, include QLearner as a resource in your project and instantiate QAgent objects with instances of QState and QAlgo through QAgent's Learn/Awaken methods.

QLearner can be made to perpetually learn and continue solving an ongoing problem (such as world domination, the stock market, or the weather) if the QState Plugin is designed in such a way such that the IsEnd() state is never reached.

About QLearner:

QLearner was originally a short AI script built into Tech Trader for optimizing stock trading strategies.  I went ahead and took the script out of Tech Trader and made QLearner a stand-alone program so that it has more flexibility to work besides just strategy optimization for stocks.  Namely, it can now apply machine learning to any situation the user builds a template for (or finds a template for...).

Like the name suggests, QLearner originally used Q-Learning algorithms but has since incorporated numerous other concepts to behave and learn in a more human-like manner.  Details on my approach to machine learning can be found in my write-up Creating Sentient Artificial Intelligence.

Back to Creations Center Index