$10,000 in Prizes at the 5th Annual (2008) “HUMIES” Awards
     For Human-Competitive Results
     Produce by Genetic and Evolutionary Computation

SUBMISSION DEADLINE: Monday May 26, 2008

www.human-competitive.org

CALL FOR ENTRIES

Techniques of genetic and evolutionary computation are being increasingly applied to difficult real-world problems—often yielding results that are not merely academically interesting, but competitive with the work done by creative and inventive humans. Starting at the Genetic and Evolutionary Computation Conference (GECCO) in 2004, prizes were awarded for human-competitive results that had been produced by some form of genetic and evolutionary computation in the previous year.

Entries are now being solicited for awards totaling $10,000 for the 2008 awards for human-competitive results that have been produced by any form of genetic and evolutionary computation (including, but not limited to genetic algorithms, genetic programming, evolution strategies, evolutionary programming, learning classifier systems, grammatical evolution, gene expression programming, differential evolution, etc.) and that have been published in the open literature between May 28, 2007 (the deadline for the previous competition) and the deadline for 2008 entries, namely Monday May 26, 2008. The competition will be held as part of the 2008 Genetic and Evolutionary Computation (GECCO-2008) Conference.

Presentations of entries will be made at the Genetic and Evolutionary Computation Conference (GECCO-2008). The awards and prizes will be announced and presented during the GECCO conference.

Cash prizes of $5,000 (gold), $3,000 (silver), and bronze (either one prize of $2,000 or two prizes of $1,000) will be awarded for the best entries that satisfy the criteria for human-competitiveness.

Find complete details at: www.human-competitive.org

GECCO 2008 Contest Problems

In conjunction with Dr. Sean Luke of George Mason University and under a research grant from NASA, Parabon Computation, Inc. has developed the Origin™ Evolutionary SDK, an extension of Dr. Luke’s ECJ framework that runs on Frontier.

Contestants will be granted free access to Parabon’s Frontier Grid Service, at 100 C of capacity, to perform evolutionary jobs for the competition, from 15 May 2008 through 6 July 2008 (the submission deadline for the competition). The Frontier SDK comes with a grid simulator that can be used locally for program development and testing before the access window opens.

Contestants must evolve a Rubik’s Cube solver. Entries must be submitted as a Java™ jar file with a class that supports a predefined Solver interface. Entries will be tested on randomly scrambled cubes. Winners will be based on the number of moves required to unscramble the test cubes and the quality of the evolutionary algorithm (quality includes factors such as autonomy, originality, and parsimony). [The details]

A 2D Packing Problem

Deadline: June 27th

This problem is a 2D variation of bin packing problems, which requires new ways to evolve with a 2D chromosome. The goal is to best pack a grid to maximize the sum of scores where every unique pair of adjacent numbers in the grid has its own score. [The details]

Entrants must turn in their best grid and a brief summary of their evolutionary algorithm. The winner is based on the best score and the quality of the evolutionary algorithm.

Human Evaluation of Evolved L-System Images

Deadline: June 27th

The goal is to evolve an L-System that will recreate a series of images in a defined number of cycles. Entrants must turn in their L-System grammar, the series of images the L-System generates and a brief summary of their evolutionary algorithm. You are provided with restrictions on the L-system grammar, target images, and a function to generate the series of images for any valid L-System. [The details]

The submitted grammars will be run on the provided L-system generator and compared by human inspection for how close they are perceived to replicate features of the executed image. The judges may or may not know what an L-system is. A human panel will judge the quality of the images.

Finding a Balanced Diet in Fractal World

Deadline: June 27th

In a more complex variant of the Santa Fe trail, the goal is to evolve an agent to search a landscape and find as much as possible of two types of food. The landscape is a fractal with varying elevations and impassible regions. Problem details, including sample training maps, and the requirements for the function, including arguments and outputs, are defined through the details link. [The details]

Entrants must turn in an ANSI C function representing the best evolved agent and a brief summary of their evolutionary algorithm. Scoring will be based on a fitness function that takes into account not only the amount of the two types of food collected but the balance between the two types of food. Submitted functions will be tested on a number of random, test maps. The quality of the evolutionary algorithm may be taken into account in the scoring.