^ Up



ZAMBESI: A Neural Net Frosh Brain Upgrade!

What is Zambesi?I think you need a new brain!

Zambesi is an experimental upgrade for the Frosh Artificial Intelligence in Legend of the Greasepole.  I implemented it as part of a project for CISC 864, a Neural Networks course. 

Zambesi replaces the complicated logic the Frosh use to make decisions with a Reinforcement Learning Network.  This network consists of neuron-like units that accept a series of inputs and generate an output that suggests what the Frosh should do next.

The inputs Zambesi uses are simple: the Frosh's distance from the Greasepole, whether or not they're being squished or stepped on, and how high up they've climbed.  This information is fed into the network of neurons, which in turn outputs one of five behaviors: climb up, jump down, hold fast, walk towards the pole, or waddle across the pyramid.

The process is called "Reinforcement Learning" because it improves the network's performance by adjusting its neural weights. A similar process governs learning in the human brain.

The algorithm used, called the associative reward-penalty rule, strengthens the neural connections that result in success, and weakens the ones that lead the frosh astray.  "Success" and "failure" are measured by a "critic" that observes the pole climb from a distance and provides an evaluation of how well the Frosh are doing.  The critic doesn't assign "credit" (or blame) to any particular frosh; instead, it averages it over everyone.   

Imagine what would happen if pre-trained Frosh could return year after year to climb the pole!  Zambesi makes this possible, by letting us save the neural weights as a sort of "genotype" to pass down information from one Frosh to another.  This genotyping is a rudimentary version of the "reproduction" that Cyberlife's "Creatures" perform.

Why Call it "Zambesi?"

Mrs. Zambesi, a "pepperpot" lady in a classic Monty Python skit, ordered a new strap-on brain from Curry's (a department store).  The model she chose was called the "Roadster."  She even had to undergo a sort of reinforcement learning technique while her brain was being fitted!  The Python gang pronounced it "Zam-Bee-Zee."

Where can I find out more?

A larger document about Zambesi is available here.  You can also read about the first round of testing here.

Can I try Zambesi?

You sure can!  I've released a version that gives you a general idea of how the Frosh look when they're under the influence of Zambesi.  They will save their weights between games, so that at least for the first few games, the Frosh should improve from one game to the next. 

Don't worry - it won't affect your original installation of Legend of the Greasepole.  Just install the original version first, upgrade to the J-section version (if you'd like) and then install Zambesi.  The original game will work just the same, and you'll have the option to check out Zambesi.  If I get the chance to play with Zambesi some more, I'll release additional versions.

As the testing results suggest, the Frosh don't improve indefinitely; in fact, they end up pretty volatile.  I mean, if you had to climb the greasepole 250 times, wouldn't you end up a little shaky?  You can delete the contents of the "weights" directory (*.wgt) if you want to "reset" the frosh brains.

Click here to go to the downloads section and get Zambesi!

The In-Depth Stuff

More Information about Zambesi

First Round of Testing Data.

About Representing Genotypes of Neural Networks

Artificial Intelligence vs Neural Networks - what's the difference?

There's a copy of The Handbook of Brain Theory and Neural Networks somewhere on the top floor of Goodwin Hall.  If you're at all interested in this stuff, you'll love it. Check it out!


Barnden, John A., "Artificial Intelligence and Neural Networks" in The Handbook of Brain Theory and Neural Networks (Michael A. Arbib, Ed.) pp 98-102.

Barto, Andrew G., "Reinforcement Learning" in The Handbook of Brain Theory and Neural Networks (Michael A. Arbib, Ed.) pp 804-809.

Barto, Andrew G., "Reinforcement Learning in Motor Control" in The Handbook of Brain Theory and Neural Networks (Michael A. Arbib, Ed.) pp 809-813.

Burke, Robert C., The Legend of the Greasepole Technical Documentation.

Cyberlife Web site,

Haykin, Simon, Neural Networks: A Comprehensive Foundation (1999) 2nd Ed.

Nolfi, Stefano and Domenico Parisi, "‘Genotypes’ for Neural Networks" in The Handbook of Brain Theory and Neural Networks (Michael A. Arbib, Ed.) pp 431-434.

^ Up

Legend of the Greasepole Website maintained by Rob Burke. Last updated October 2004.