Very Low Activity

Project Summary

  Analyzed 2 days ago based on code collected 2 days ago.

Experiments in applying evolutionary algorithms, neural networks and other AI/CI algorithms to Super Mario Bros.

Benchmark for macnine learning and artificial intelligence based on Super Mario Bros

What?This is an open source software for AI, Machine Learning algorithms benchmarking, written in Java with TCP interface and example agents in Java and Python. This software suits for research, teaching and self-learning. Starting from very simple examples you have ability to dive into very complex tasks. JNI is going to be supported fairly soon.

Why?Got boring one day from walking just the mazes and came up with idea to create a universal benchmark with simple interface and entertaining content.

When?This project was started in March 2009. Mario AI Competition was hold @ ICE-GIC in London on August, 24th and CIG in Milano on September, 7th, 2009. Currently approaching and working on organizing AI Mario Championship 2010.

Who?by Julian Togelius and Sergey Karakovskiy with participant of Tom Schaul and Jan Koutnik.

Where?@ IDSIA

Share

In a Nutshell, marioai...

Languages

Java
86%
C++
5%
7 Other
9%
 
 

Lines of Code

 

Activity

30 Day Summary Apr 17 2013 — May 17 2013

12 Month Summary May 17 2012 — May 17 2013

  • 0 Commits Down -1 (100%) from previous 12 months
  • 0 Contributors Down -1 (100%) from previous 12 months

Community

 
 
 

Creative Commons License Copyright © 2013 Black Duck Software, Inc. and its contributors, Some Rights Reserved. Unless otherwise marked, this work is licensed under a Creative Commons Attribution 3.0 Unported License . Ohloh ® and the Ohloh logo are trademarks of Black Duck Software, Inc. in the United States and/or other jurisdictions. All other trademarks are the property of their respective holders.