Ms. Pac-Man Framework Icon

Ms. Pac-Man Framework

Using reinforcement learning with relative input to train Ms. Pac-Man

Add a Review
0 Downloads (This Week)
Last Update:
  Browse Code SVN Repository



This Java-application contains all required components to simulate a game of Ms. Pac-Man and let an agent learn intelligent playing behaviour using reinforcement learning and either Q-Learning or SARSA.

The framework was developed by Luuk Bom and Ruud Henken, under supervision of Marco Wiering, Department of Artificial Intelligence, University of Groningen. It formed the basis of a bachelor's thesis titled "Using reinforcement learning with relative input to train Ms. Pac-Man", L.A.M. Bom (2012).

Ms. Pac-Man Framework Web Site


  • (Graphical) simulation of the game Ms. Pac-Man
  • Uses a small number of clever relative inputs to represent the game environment
  • Reinforcement learning with either Q-Learning or SARSA
  • Highly configurable and easy to tweak
  • Results can be exported to .CSV or plotted in graphs
  • Extensive documentation


Other Useful Business Software

The Sight of Sound Icon

­ Improve VoIP Visibility from SIP to RTP

The Sight of Sound Icon
Cloudbased voice solutions are common in enterprise networks and frustrating for operations teams to manage. Simplify VoIP monitoring by having a proactive analysis of on-prem, hybrid and UCaaS voice services. Try the ThousandEyes VoIP monitoring solution today, free.
Write a Review

User Reviews

Be the first to post a review of Ms. Pac-Man Framework!

Additional Project Details

User Interface

Java Swing, Java AWT

Programming Language




Thanks for helping keep SourceForge clean.

Screenshot instructions:
Red Hat Linux   Ubuntu

Click URL instructions:
Right-click on ad, choose "Copy Link", then paste here →
(This may not be possible with some types of ads)

More information about our ad policies

Briefly describe the problem (required):

Upload screenshot of ad (required):
Select a file, or drag & drop file here.

Please provide the ad click URL, if possible:

Get latest updates about Open Source Projects, Conferences and News.

No, thanks