7CCSMML1 (Machine Learning)
Coursework 2
(Version 1.0)
1 Overview
For this coursework, you will have to implement a reinforcement learning algorithm. Your code will
again be controlling Pacman, in the classic game, and the reinforcement learning algorithm will be
helping Pacman choose how to move. Your reinforcement learning algorithm should be able, once
it has done its learning, to be able to play a pretty good game, and its ability ot play a good game
will be part of what we assess.
No previous experience with Pacman (either in general, or with the speci c UC Berkely AI imple-
mentation that we will use) is required.
This coursework is worth 10% of the marks for the module.
Note: Failure to follow submission instructions will result in a deduction of 10% of the marks you
earn for this coursework.
2 Getting started
2.1 Start with Pacman
The Pacman code that we will be using for the 7CCSMML1 coursework was developed at UC
Berkeley for their AI course. The folk who developed this code then kindly made it available to
everyone. The homepage for the Berkeley AI Pacman projects is here:
http://ai.berkeley.edu/
Note that we will not be doing any of their projects. Note also that the code only supports Python
2.7, so that is what we will use1.
You should:
1. Download:
pacman-cw2.zip
from KEATS.
2. Save that le to your account at KCL (or to your own computer).
3. Unzip the archive.
This will create a folder pacman-cw2
1If you insist on using Python 3, you are on your own in terms of support, and if the code you sbmit does not
work (which is likely) you will lose marks.
1 parsons-michael-raphael-cw2