Computer Science Department

CS4341 ❏ Artificial Intelligence ❏ B07

Mon, Tue, Thu, Fri - 1:00 - AK 233
Prof. David C. Brown, Fuller Lab 131, (508) 831-5618, dcb at cs.wpi.edu

Version: Thu Nov 29 21:34:50 EST 2007

PROJECT 3 - Finding the Best Search Team

All projects will be graded out of 100 points for convenience, and will be adjusted later to conform to the class grading scheme already provided to you. Grading will be subtractive. That is, you start with 100 points, and points will be deducted for problems found. This produces lower scores, is harder to grade, but is much fairer and more consistent.

    The grading will be divided into consideration of: * 10 pts Presentation (i.e., style, layout, comments) * 30 pts Required (i.e., what the problem description asked for) * 60 pts Demonstration (i.e., the output from and actions by the system -- layout, clarity, completeness, how well tested). 10 PRESENTATION: Clear documentation and descriptions. Good coding standards. Clear system output. Readable tests and explanations. 30 REQUIRED: - uses GA technique including mutation and crossover - uses rank-space method (quality rank and diversity rank) - uses team representation given in problem (or similar) - starts with the one team provided - starts each new population with 4 rule sets - does all possible crossovers between the current rules sets - applies mutation transformation to each member of the current population - doesnt allow duplicate teams in a population - evaluates team fitness using 5 pseudo-random placements, as well as the seeing/hearing approximation - have provided items: # Brief, clear documentation that describes the design of your GA system. What special algorithms or data structures were used? # A description of, and rationale for, your biasing method. # A description of, and rationale for, your team diversity measure. # A description of, and rationale for, your stopping condition. # The code for the system (which must be well commented). # The clear, readable output from the test/demonstration runs. (These should not be annotated). # Output in "demonstration" format. # Output of condensed team representation for each generation. 60 DEMONSTRATION: All aspects working & correct. -- teams formed according to rules -- mutation & crossover as prescribed -- duplicate teams discarded -- pseudo-random placement -- seeing/hearing algorithm -- team quality calculations -- team diversity calculation -- rank-space method -- fitness score -- stopping condition -- best team found How well tested (look for variations due to randomness). -- include case of the landscape provided. -- include one or more "special cases" that have been used to convince yourself that the system is working. Completeness of messages in "demonstration" output. (i.e., we understand what's happening) (i.e., it is an explanation, not a trace) (N.B., for this project this is very important!) Include an explanation of why you think that the team found by the GA is the best. _________________________________