Teaching intelligent agents through game problems
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Research, Society and Development |
Texto Completo: | https://rsdjournal.org/index.php/rsd/article/view/1793 |
Resumo: | 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. |
id |
UNIFEI_aeb4c33794d4264dec42dcb2371dac1f |
---|---|
oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/1793 |
network_acronym_str |
UNIFEI |
network_name_str |
Research, Society and Development |
repository_id_str |
|
spelling |
Teaching intelligent agents through game problemsEnseñar agentes inteligentes através de problemas de juegoEnsino de agentes inteligentes por meio de problemas em jogosAprendizagem Baseada em ProblemasAgentes InteligentesJogosEstratégias de BuscaAlgoritmos GenéticosRedes Neurais Artificiais.Aprendizaje Basado en ProblemasAgentes InteligentesJuegosEstrategias de BúsquedaAlgoritmos GenéticosRedes Neuronales Artificiales.Problem Based LearningIntelligent AgentsGamesSearch StrategiesGenetic AlgorithmsArtificial Neural Networks.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.La enseñanza de agentes inteligentes, presentada en este estudio, se realizó a través del método de Aprendizaje Basado en Problemas. Pac-Man fue seleccionado como estudio de caso. El proceso de aprendizaje constructivo se llevó a cabo a través de tres etapas, a saber: (i) la implementación de agentes básicos, con el único propósito de completar la ruta en el mapa; (ii) la implementación de agentes reales, considerando la existencia de fantasmas; y, finalmente, (iii) la implementación de agentes de aprendizaje inteligente. Como parte del proceso de construcción de conocimiento, cada nuevo agente propuesto por el estudiante fue creado para resolver problemas encontrados en el análisis de desempeño de agentes anteriores. En la primera etapa de desarrollo, se observó una mejora del rendimiento del 33.45% del Agente 1 al Agente 6. En la segunda etapa, considerando el juego real, el Agente 8 mostró un aumento del rendimiento del 20.49% en comparación con el Agente 7 En la tercera etapa, se utilizaron redes neuronales artificiales y algoritmos genéticos, lo que nos permitió crear un agente capaz de aprender y completar el mapa solo. Por lo tanto, fue posible demostrar que las técnicas seleccionadas fueron eficientes para mejorar el nivel de inteligencia de los agentes propuestos para el juego en cuestión. Además, el uso de este método de enseñanza resultó en una mayor participación del estudiante en la disciplina de Inteligencia Artificial, favoreciendo su dominio en las técnicas de construcción inteligente de agentes, y contribuyendo a su interés en esta área de estudio.O ensino de agentes inteligentes, apresentado neste estudo, foi realizado por meio do método de Aprendizagem Baseada em Problemas. O jogo Pac-Man foi selecionado como estudo de caso. O processo de aprendizado construtivo foi executado mediante três etapas, sendo elas: (i) a implementação de agentes básicos, com objetivo apenas de completar o percurso no mapa; (ii) a implementação de agentes reais, considerando a existência de fantasmas; e, por fim, (iii) a implementação de agentes inteligentes com capacidade de aprendizado. Como parte do processo de construção do conhecimento, cada novo agente proposto pelo discente foi criado com a finalidade de solucionar problemas encontrados nas análises de desempenho de agentes anteriores. Na primeira etapa de desenvolvimento foi observada uma melhora de 33,45% no desempenho do Agente 1 para o Agente 6. Na segunda etapa, considerando o jogo real, o Agente 8 apresentou incremento de desempenho de 20,49% quando comparado ao Agente 7. Na terceira etapa, foram utilizadas redes neurais artificiais e algoritmos genéticos, o que permitiu criar um agente capaz de aprender e completar o mapa sozinho. Assim, foi possível comprovar que as técnicas selecionadas mostraram-se eficientes ao melhorar o nível de inteligência dos agentes propostos para o jogo em questão. Além disso, o emprego deste método de ensino resultou em um maior envolvimento do discente com a disciplina de Inteligência Artificial, favorecendo o domínio deste aluno em técnicas de construção de agentes inteligentes, bem como contribuindo para maior interesse do mesmo por esta área de estudo.Research, Society and Development2020-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://rsdjournal.org/index.php/rsd/article/view/179310.33448/rsd-v9i1.1793Research, Society and Development; Vol. 9 No. 1; e129911793Research, Society and Development; Vol. 9 Núm. 1; e129911793Research, Society and Development; v. 9 n. 1; e1299117932525-3409reponame:Research, Society and Developmentinstname:Universidade Federal de Itajubá (UNIFEI)instacron:UNIFEIporhttps://rsdjournal.org/index.php/rsd/article/view/1793/1551Copyright (c) 2020 Luis Otavio Rigo Jr.info:eu-repo/semantics/openAccessSilva, Gustavo AugustoRigo Júnior, Luis Otavio2020-08-19T03:04:08Zoai:ojs.pkp.sfu.ca:article/1793Revistahttps://rsdjournal.org/index.php/rsd/indexPUBhttps://rsdjournal.org/index.php/rsd/oairsd.articles@gmail.com2525-34092525-3409opendoar:2024-01-17T09:26:41.943120Research, Society and Development - Universidade Federal de Itajubá (UNIFEI)false |
dc.title.none.fl_str_mv |
Teaching intelligent agents through game problems Enseñar agentes inteligentes através de problemas de juego Ensino de agentes inteligentes por meio de problemas em jogos |
title |
Teaching intelligent agents through game problems |
spellingShingle |
Teaching intelligent agents through game problems Silva, Gustavo Augusto Aprendizagem Baseada em Problemas Agentes Inteligentes Jogos Estratégias de Busca Algoritmos Genéticos Redes Neurais Artificiais. Aprendizaje Basado en Problemas Agentes Inteligentes Juegos Estrategias de Búsqueda Algoritmos Genéticos Redes Neuronales Artificiales. Problem Based Learning Intelligent Agents Games Search Strategies Genetic Algorithms Artificial Neural Networks. |
title_short |
Teaching intelligent agents through game problems |
title_full |
Teaching intelligent agents through game problems |
title_fullStr |
Teaching intelligent agents through game problems |
title_full_unstemmed |
Teaching intelligent agents through game problems |
title_sort |
Teaching intelligent agents through game problems |
author |
Silva, Gustavo Augusto |
author_facet |
Silva, Gustavo Augusto Rigo Júnior, Luis Otavio |
author_role |
author |
author2 |
Rigo Júnior, Luis Otavio |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Silva, Gustavo Augusto Rigo Júnior, Luis Otavio |
dc.subject.por.fl_str_mv |
Aprendizagem Baseada em Problemas Agentes Inteligentes Jogos Estratégias de Busca Algoritmos Genéticos Redes Neurais Artificiais. Aprendizaje Basado en Problemas Agentes Inteligentes Juegos Estrategias de Búsqueda Algoritmos Genéticos Redes Neuronales Artificiales. Problem Based Learning Intelligent Agents Games Search Strategies Genetic Algorithms Artificial Neural Networks. |
topic |
Aprendizagem Baseada em Problemas Agentes Inteligentes Jogos Estratégias de Busca Algoritmos Genéticos Redes Neurais Artificiais. Aprendizaje Basado en Problemas Agentes Inteligentes Juegos Estrategias de Búsqueda Algoritmos Genéticos Redes Neuronales Artificiales. Problem Based Learning Intelligent Agents Games Search Strategies Genetic Algorithms Artificial Neural Networks. |
description |
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. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-01-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/1793 10.33448/rsd-v9i1.1793 |
url |
https://rsdjournal.org/index.php/rsd/article/view/1793 |
identifier_str_mv |
10.33448/rsd-v9i1.1793 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/1793/1551 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2020 Luis Otavio Rigo Jr. info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2020 Luis Otavio Rigo Jr. |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Research, Society and Development |
publisher.none.fl_str_mv |
Research, Society and Development |
dc.source.none.fl_str_mv |
Research, Society and Development; Vol. 9 No. 1; e129911793 Research, Society and Development; Vol. 9 Núm. 1; e129911793 Research, Society and Development; v. 9 n. 1; e129911793 2525-3409 reponame:Research, Society and Development instname:Universidade Federal de Itajubá (UNIFEI) instacron:UNIFEI |
instname_str |
Universidade Federal de Itajubá (UNIFEI) |
instacron_str |
UNIFEI |
institution |
UNIFEI |
reponame_str |
Research, Society and Development |
collection |
Research, Society and Development |
repository.name.fl_str_mv |
Research, Society and Development - Universidade Federal de Itajubá (UNIFEI) |
repository.mail.fl_str_mv |
rsd.articles@gmail.com |
_version_ |
1797052829346562048 |