WUBWorld


This simulation was created as part of course CS-263, taught by Lee Spector and Jon Klein. All materials in this page, except the video below, were generated by that course. Original course materials can be found at http://hampshire.edu/lspector/cs263/cs263s04.html


Video of WUBWorld tar ball with necessary files

There are four versions of the simulation, each adding newer features. Here is the text describing each version, which is also included in the ABOUT.txt file in the tar file provided above.

WUBWorld_1

    A breve simulation introducing "WUBWorld", where students can
    program autonomous agents to interact with a dynamic environment.
    In this first version, students learn to direct the agent to
    collect pieces of food.

WUBWorld_2

    An update to WUBWorld which introduces obstacles and enemies
    into the environment.  The agent must now eat food in order to
    survive, while avoiding enemies and navigating around obstacles.

WUBWorld_3

    A version of WUBWorld which includes code for building neural
    networks.  It also allows the agents to attack enemies by
    firing towards them.  Students can use the neuron class to make
    decisions about when to attack or how to move.
   
WUBWorld_4
   
    The final update to WUBWorld introduces a whole mess of
    complications: smarter enemies, enemy rebirth, and deadly "shock
    waves".  To cope with the more complicated world, agents are
    given the ability to evolve.  When an agent dies, it can be
    reborn, selecting traits and behaviors from more successful
    agents.