1) PAPER TITLE GP-RARS: Evolving Controllers for the Robot Auto Racing Simulator 2) AUTHORS Yehonatan Shichel, shichel@gmail.com Moshe Sipper, sipper@cs.bgu.ac.il Physical address for all: Department of Computer Science, Ben-Gurion University of the Negev, Beer-Sheva 84105, ISRAEL 3) CORRESPONDING AUTHOR Moshe Sipper 4) ABSTRACT We use evolutionary computation techniques to create real-time reactive controllers for a race-car simulation game: RARS (Robot Auto Racing Simulator). Using genetic programming to evolve driver controllers, we create highly generalized game-playing agents, able to outperform most human-crafted controllers and all machine-designed ones on a variety of game tracks. 5) CRITERIA (B) The result is equal to or better than a result that was accepted as a new scientific result at the time when it was published in a peer-reviewed scientific journal. (F) The result is equal to or better than a result that was considered an achievement in its field at the time it was first discovered. (G) The result solves a problem of indisputable difficulty in its field. (H) The result holds its own or wins a regulated competition involving human contestants (in the form of either live human players or human-written computer programs). 6) WHY THE RESULT SATISFIES THE CRITERIA Why the result satisfies criterion (B) -------------------------------------- Using genetic programming to evolve driver controllers we were able to outperform human-crafted controllers and machine-designed ones on a variety of game tracks. As such, the result is clearly better than previously published ones. Why the result satisfies criteria (F,G) ----------------------------------------- Programming controllers for simulated race cars is arduous, as evidenced in the proliferation of such competitions in recent years. We were able to show significant improvement over previous solutions to the problem. Why the result satisfies criterion (H) -------------------------------------- Our evolved drivers were able to beat the competition, attaining a top accumulated score on 16 tracks, *none* of which were seen during training. The tables on p. 8 of the paper clearly show the superiority of our evolved controllers, both against machine-learning techniques as well as against human-written controllers. 7) CITATION Y. Shichel and M. Sipper, "GP-RARS: Evolving controllers for the Robot Auto Racing Simulator", Memetic Computing Journal, 2011, accepted for publication. 8) STATEMENT OF PRIZE DISTRIBUTION Any prize money, if any, is to be divided equally among the two co-authors. 9) COMPARISON TO OTHER HUMAN-COMPETITIVE ENTRIES Controlling a moving vehicle is considered a complex problem, both in simulated and real-world environments. Dealing with physical forces, varying road conditions, unexpected opponent behavior, damage control, and many other factors, render the car-racing problem a fertile grounds for artificial intelligence research, and an enormous challenge for developers of race-car controllers. The fact that we were able to evolve not only competent controllers but indeed winning ones meets the human-competitive challenge to the full. In addition to the undisputed performance of our game controllers, the evolved solutions reflect two intrinsic qualities that are not always observed in human-competitive solutions: generalization and simplicity. The controllers were able to perform outstandingly on diverse instances of the given problem, which were not included in the training set, and hence are highly general. In addition, the evolved source code is simple and clear---as shown in Section 5--- thus enabling humans to understand the inner workings of the controllers and embed the evolved results in both human-made and computer-made future solutions. Last, but not least, beyond the various comparative measures and analyses, showing the winning performance of our controllers, p. 12 demonstrates that the evolved drivers really are doing a fine job of driving about the course, which can be readily appreciated by the naked eye...