Teaching intelligent agents through game problems
DOI:
https://doi.org/10.33448/rsd-v9i1.1793Keywords:
Problem Based Learning; Intelligent Agents; Games; Search Strategies; Genetic Algorithms; Artificial Neural Networks.Abstract
The teaching of intelligent agents, presented in this study, was performed through the Problem Based Learning method. Pac-Man was selected as a case study. The constructive learning process was carried out through three stages, namely: (i) the implementation of basic agents, with the sole purpose of completing the route on the map; (ii) the implementation of real agents, considering the existence of ghosts; and, finally, (iii) the implementation of intelligent learning agents. As part of the knowledge building process, each new agent proposed by the student was created to solve problems found in the performance analysis of previous agents. In the first stage of development a performance improvement of 33.45% was observed from Agent 1 to Agent 6. In the second stage, considering the actual game, Agent 8 showed a performance increase of 20.49% when compared to Agent 7. In the third stage, artificial neural networks and genetic algorithms were used, which allowed us to create an agent capable of learning and completing the map alone. Thus, it was possible to prove that the selected techniques were efficient in improving the intelligence level of the agents proposed for the game in question. In addition, the use of this teaching method resulted in a greater involvement of the student with the Artificial Intelligence discipline, favoring the student's mastery in intelligent agent construction techniques, as well as contributing to his interest in this area of study.
References
Arzt, S. (2016). Deep learning cars [Site]. Acesso em 20 de maio, em https://arztsamuel.github.io/ en/projects/unity/deepCars/deepCars.html
Barone, D. A. C. & Silveira, S. R. (1998). Jogos educativos computadorizados utilizando a abordagem de algoritmos genéticos. Congresso da Rede Iberoamericana de Informática na Educação, Brasília, DF, Brasil.
Bastos, R. & Jaques, P. (2010). Antares, um sistema web de consulta de rotas de ônibus como serviço público. Revista Brasileira de Computação Aplicada, 2(1), 41–56.
Catarina, A. S. & Bach, S. L. (2003). Estudo do efeito dos parâmetros genéticos sobre a solução otimizada e sobre o tempo de convergência em algoritmos genéticos com codificações binária e real. Acta Scientiarum. Technology, 25(2), 147–152.
Costa, N. M. S. & Netto, J. F. M. (2009). Desenvolvimento de um jogo educacional multiusuário usando bluetooth. Relatório de Iniciação Científica do Programa PIBIC 2008–2009, Universidade Federal do Amazonas, UFAM, Brasil.
Cormen, T. H.; Leiserson, C. E.; Rivest, R. L. & Stein, C. (2009). Introduction to Algorithms (3rd ed). Cambridge, Massachusetts: The MIT Press.
Crocomo, M. K (2008). Um algoritmo evolutivo para aprendizado on-line em jogos eletrônicos. (Dissertação de mestrado). Instituto de Ciências Matemáticas e de Computação – ICMC-USP, São Carlos, SP, Brasil.
Darwin, C. (1859). On the Origin of Species by Means of Natural Selection. Murray, London.
Deza, M. M. & Deza, E. (2016). Encyclopedia of Distances (4th ed.). Springer-Verlag.
Ficheman, I. K.; Assis, G. A.; Corrêa, A. G. D.; Netto, M. L. & Lopes, R. D. (2006). Educatrans: um jogo para educação no trânsito. Brazilian Symposium on Computers in Education (Simpósio Brasileiro de Informática na Educação – SBIE), 19–21, UNB/UCB, Brasília, DF, Brasil, XVII SBIE.
Gallagher, M. & Rayan, A. (2003). Learning to play pac-man: An evolutionary, ruse-based approach. The 2003 Congress on Evolutionary Computation, CEC, Camberra, ACT, Australia. doi:10.1109/CEC.2003.1299397
Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization and Machine Learning. MA: Addison-Wesley Reading.
Grando, A. & Tarouco, L. M. R. (2008). O uso de jogos educacionais do tipo rpg na educação. CINTED-UFRGS, Revista Novas Tecnologias na Educação, vol. 6, n. 1. doi: https://doi.org/10.22456/1679-1916.14403
Haykin, S. S. (2001). Redes Neurais - Princípios e Prática (2nd ed.). Bookman.
Marquardt, D. W. (1963). An algorithm for least-squares estimation of non-linear parameters. Journal of the Society for Industrial and Applied Mathematics, 11(2), 431–441. doi:10.1137/0111030
Mitchell, M. (1996). An Introduction to Genetic Algorithms. Cambridge. MA: The MIT Press.
Mitchell, T. (1997). Machine Learning. McGraw Hill Higher Education.
Oliveira, F. F.; Piteri, M. A. & Menequette, M. (2014). Desenvolvimento de uma plataforma de software para a modelagem digital de terrenos baseada em tin. Boletim de Ciências Geodésicas, Revista UFPR, Curitiba, PR, Brasil, 20(1), 117-131. doi: 10.1590/S1982-21702014000100008
Patel, A. (2018). Pathfinding for tower defense cars [Site]. Acesso em 01 de novembro, em www.redblobgames.com/pathfinding/tower-defense/.
Pinheiro, E.; Kubo, C. C. ; Rangel, M. S. ; Arcari, T. A. & Dias, C. G. (2009). Navegação autônoma de um agente inteligente: Um estudo comparativo usando lógica fuzzy e algoritmo de busca a*. Exacta, São Paulo, SP, Brasil, 7(1), 87–98. doi: 10.5585/exacta.v7i1.1531
Rigo Jr., L. O. (2005). Evolução de autômatos celulares para a previsão de séries temporais correlacionadas. (Dissertação de mestrado). Programa de Engenharia de Sistemas e Computação / COPPE - UFRJ, Rio de Janeiro, RJ, Brasil.
Ribeiro, L. M. P. (2008). Otimização e dimensionamento de treliças panas de madeira empregando o método dos algoritmos genéticos. (Dissertação de mestrado). Programa de Engenharia Civil, Universidade Federal de Uberlândia, Uberlândia, MG, Brasil.
Rumelhart, D. E.; Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536.
Russell, S. J. & Norvig, P. (2009). Artificial intelligence: a modern approach (3rd ed.). Pearson.
Seidel, I. (2015). Inteligência artificial com dinossauro da google [Video]. Acesso em 20 de maio, em https://www.youtube.com/watch?v=P7XHzqZjXQs&t=71s
Silva, A. B. D.; Bispo, A. C. K. A.; Rodriguez, D. G. & Vasquez, F. I. F. (2018). Problem-based learning: A proposal for structuring pbl and its implications for learning among students in an undergraduate management degree program. REGE Revista de Gestão, 25(2), 160–177. doi: 10.1108/REGE-03-2018-030
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
