Penerapan Algoritma Genetika dan Algoritma Ghost Framework pada Game Ms. Pacman
Abstract
Pacman merupakan salah satu game klasik yang terkenal pada dekade 80-an dan masih sampai sekarang menarik untuk menjadi objek penelitian tentang penerapan berbagai konsep Artificial Intellegent (AI). Tujuan utama dari game ini adalah, mendapatkan poin sebanyak-banyaknya sambil menghidar dari kejaran ghost dan mendapatkan poin tambahan saat memakan ghost setelah mendapatkan pil super. Pergerakan masing-masing ghost ditentukan oleh algoritma DFS dan BFS yang diterapkan pada Ghost Framework. Algoritma tersebut sering digunakan untuk membandingkan algoritma lain dalam hal efektifitas. Penulis memanfaatkan Algoritma DFS dan BFS pada ghost digame Pacman untuk membandingkan keefektifan Algoritma Genetika (GA). Penulis menerapkan Algoritma Genetika pada player Pacman sebagai pengganti control. Terminal akan bertugas untuk mengambil nilai semua kemungkinan arah gerakan di setiap waktu selama permainan. Berdasarkan nilai-nilai ini pengontrol dapat mengontrol MS. Pacman melawan Ghost framework. Dengan desain ini, Penulis mengurangi kompleksitas solusi GA dengan menghapus semua control tindakan tugas manajemen dari system. Setelah melakukan beberapa pengujian, Penulis mendapatkan hasil dimana GA menghasilkan rerata score 8,330 yang lebih tinggi dibandingkan dengan player amatir dan kontroler lain. Dari hasil yang tersedia, Penulis menyimpulkan bahwa kinerja GA sebagai controller MS. Pacman dapat dikatakan baik.
Kata Kunci — Algoritma Genetika, Pacman, Ghost Framework
Pacman is one of the famous classic games in the 80s and is still interesting to be the object of research on Artificial Intelligence (AI). The main goal of this game is to get as many points as possible while avoiding ghost chases and get extra points when eating ghost after getting super pills. The movement of each ghost is determined by the DFS and BFS algorithms that are applied to Ghost Framework. The algorithm is often used to compare other algorithms in terms of effectiveness. Writer use the DFS and BFS Algorithm on ghost in the Pacman game to compare the effectiveness of the Genetic (GA) Algorithm. The terminal will take the value of all possible direction of movement during the game. Based on these values the controller can control MS. Pacman against Ghost framework. With this design, Writer reduce the complexity of the GA solution by removing all management actions from the control system. After doing some testing, Writer get results where GA produces a higher score compared to other amateur players and controllers. From available results, Writer conclude that the performance of GA as a MS. Pacman controller is good.
Keywords — Genetic Algorithm, Pacman, Ghost Framework
Full Text:
PDFReferences
M. J. Wolf, Ed., 11 2007. The Video Game Explosion: A History from PONG to PlayStation and Beyond. Greenwood.
Müller, M., 2010, Pacman Writerreldrecord beklonken en het hele verhaal (in Dutch), https://web.archive.org/web/20120227102904/http://www.ng-gamer.nl/game-nieuws/11117 _ pacman-wereldrecord-beklonken-en-het-hele-verhaal/.
Frayudha, A. D., As’ari, T. H., Implementasi Genetic Algorithm untuk pergerakan Ghost di permainan Pac Man, UIN Malang, https://www.academia.edu/15458673/Implementasi_ Genetic_Algorithm_untuk_pergerakan_Ghost_di_permainan_Pac_Man, diakses tanggal 27 Desember 2018.
Bell, N., Fang, X. H., Hughes, R., Kendall, G., O’Reilly, E., Qiu S. H., 2010, Ghost direction detection and other innovations for Ms. Pacman, 2010 IEEE Symposium on Computational Intelligence and Games (CIG), Copenhagen, September.
Holland, J. H., 1975, Adaptation in Natural and Artificial Systems, An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence, A Bradford Book, Cambridge.
Kinnear, K. E. (1994). Kinnear, K., E, 1994, A Perspective on the Work in this Book. In K. E. Kinnear (Ed.), Advances in Genetic Programming, MIT Press, Cambridge.
Goldberg, D. E., 1989, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Writersley Publishing, Boston
Carr, J, 2014, An Introduction to Genetic Algorithms, https://www.semanticscholar.org/ paper/An-Introduction-to-Genetic-Algorithms-Carr/e9f8d49686a4c8d99d0a5ceba85c4508c 30d57c4
Koza, J. R., 1992. Genetic Programming On the Programming of Computers by Means of Natural Selection, A Bradford Book, Cambridge.
Alhejali, A. M., Lucas, S. M., 2010, Evolving diverse Ms. Pac-Man playing agents using genetic programming, UK Workshop on Computational Intelligence (UKCI), Colchester, 8-10 September.
DOI: https://doi.org/10.24076/citec.2018v5i3.206
Refbacks
- There are currently no refbacks.
Indexed by:
Dedicated to: