Deep learning game agents in Bomberland: A comparative analysis

Bomberland is a modified clone of the popular arcade game Bomberman developed for an AI Agent Competition, adding a layer of cooperation using teams. This project aims to highlight how popular Deep Learning algorithms for game agents, Deep Q Learning and NEAT, perform against added complexity throug...

Full description

Autores:
Campo Cotes, Santiago Rafael
Tipo de recurso:
Trabajo de grado de pregrado
Fecha de publicación:
2025
Institución:
Universidad de los Andes
Repositorio:
Séneca: repositorio Uniandes
Idioma:
eng
OAI Identifier:
oai:repositorio.uniandes.edu.co:1992/75569
Acceso en línea:
https://hdl.handle.net/1992/75569
Palabra clave:
Artificial Intelligence
Game Agents
NEAT
Machine Learning
Ingeniería
Rights
openAccess
License
Attribution 4.0 International
id UNIANDES2_0c4c5fa02abfb0e8a26f25a4f89b09cd
oai_identifier_str oai:repositorio.uniandes.edu.co:1992/75569
network_acronym_str UNIANDES2
network_name_str Séneca: repositorio Uniandes
repository_id_str
dc.title.eng.fl_str_mv Deep learning game agents in Bomberland: A comparative analysis
title Deep learning game agents in Bomberland: A comparative analysis
spellingShingle Deep learning game agents in Bomberland: A comparative analysis
Artificial Intelligence
Game Agents
NEAT
Machine Learning
Ingeniería
title_short Deep learning game agents in Bomberland: A comparative analysis
title_full Deep learning game agents in Bomberland: A comparative analysis
title_fullStr Deep learning game agents in Bomberland: A comparative analysis
title_full_unstemmed Deep learning game agents in Bomberland: A comparative analysis
title_sort Deep learning game agents in Bomberland: A comparative analysis
dc.creator.fl_str_mv Campo Cotes, Santiago Rafael
dc.contributor.advisor.none.fl_str_mv Takahashi Rodríguez, Silvia
dc.contributor.author.none.fl_str_mv Campo Cotes, Santiago Rafael
dc.contributor.jury.none.fl_str_mv Takahashi Rodríguez, Silvia
dc.subject.keyword.eng.fl_str_mv Artificial Intelligence
Game Agents
NEAT
Machine Learning
topic Artificial Intelligence
Game Agents
NEAT
Machine Learning
Ingeniería
dc.subject.themes.spa.fl_str_mv Ingeniería
description Bomberland is a modified clone of the popular arcade game Bomberman developed for an AI Agent Competition, adding a layer of cooperation using teams. This project aims to highlight how popular Deep Learning algorithms for game agents, Deep Q Learning and NEAT, perform against added complexity through cooperative, adversarial, and stochastic elements.
publishDate 2025
dc.date.accessioned.none.fl_str_mv 2025-01-22T16:04:16Z
dc.date.available.none.fl_str_mv 2025-01-22T16:04:16Z
dc.date.issued.none.fl_str_mv 2025-01-21
dc.type.none.fl_str_mv Trabajo de grado - Pregrado
dc.type.driver.none.fl_str_mv info:eu-repo/semantics/bachelorThesis
dc.type.version.none.fl_str_mv info:eu-repo/semantics/acceptedVersion
dc.type.coar.none.fl_str_mv http://purl.org/coar/resource_type/c_7a1f
dc.type.content.none.fl_str_mv Text
dc.type.redcol.none.fl_str_mv http://purl.org/redcol/resource_type/TP
format http://purl.org/coar/resource_type/c_7a1f
status_str acceptedVersion
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/1992/75569
dc.identifier.instname.none.fl_str_mv instname:Universidad de los Andes
dc.identifier.reponame.none.fl_str_mv reponame:Repositorio Institucional Séneca
dc.identifier.repourl.none.fl_str_mv repourl:https://repositorio.uniandes.edu.co/
url https://hdl.handle.net/1992/75569
identifier_str_mv instname:Universidad de los Andes
reponame:Repositorio Institucional Séneca
repourl:https://repositorio.uniandes.edu.co/
dc.language.iso.none.fl_str_mv eng
language eng
dc.relation.references.none.fl_str_mv Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., & Zaremba, W. (2016, June 6). OpenAI Gym. Retrieved from OpenAI: https://arxiv.org/abs/1606.01540
Gymnasium Team. (2023). Gymnasium. Retrieved from Farama Foundation: https://gymnasium.farama.org/
Krabbenhöft, H. N. (2022, May 12). Bomberland AI - Part I - Lingo, Replays and TensorFlow Observations. Retrieved from Hajos Personal Blog: https://hajo.me/blog/2022/05/12/coder-one-bomberland-tutorial-1of3-introduction-replays-and-conversion-to-tensorflow/
MacWha, R. (2021, March 3). Evolving AIs using a NEAT algorithm. Retrieved from Medium: https://macwha.medium.com/evolving-ais-using-a-neat-algorithm-2d154c623828
Mnih, V., Kavukcuouglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., . . . Antonoglou, I. (2015). Human-level control through deep reinforcement learning. Nature 518, 529-542.
OpenAI Five Team. (2018, June 25). OpenAI Five. Retrieved from OpenAI: https://openai.com/research/openai-five
Orkin, J. (2006). Three States and a Plan: The A.I. of F.E.A.R. Game Developers Conference.
Stanley, K. O., & Miikulainen, R. (2002). Evolving Neural Networks through Augmenting Topologies. Evolutionary Computation 10(2), 99-127.
TF-Agents Authors. (2023). Introduction to RL and Deep Q Networks. Retrieved from Tensorflow: https://www.tensorflow.org/agents/tutorials/0_intro_rl
The Interactive Agent Team. (2022, November 23). Building Interactive Agents in Video Game Worlds. Retrieved from Google Deepmind: https://deepmind.google/discover/blog/building-interactive-agents-in-video-game-worlds/
Zhang, J. (2021, November 29). Bomberland. Retrieved from CoderOne: https://www.gocoder.one/blog/bomberland-multi-agent-artificial-intelligence-competition/
dc.rights.en.fl_str_mv Attribution 4.0 International
dc.rights.uri.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.accessrights.none.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.coar.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.extent.none.fl_str_mv 16 páginas
dc.format.mimetype.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidad de los Andes
dc.publisher.program.none.fl_str_mv Ingeniería de Sistemas y Computación
dc.publisher.faculty.none.fl_str_mv Facultad de Ingeniería
dc.publisher.department.none.fl_str_mv Departamento de Ingeniería de Sistemas y Computación
publisher.none.fl_str_mv Universidad de los Andes
institution Universidad de los Andes
bitstream.url.fl_str_mv https://repositorio.uniandes.edu.co/bitstreams/6dc8a210-14e1-41bc-8fb7-cc727f7964fa/download
https://repositorio.uniandes.edu.co/bitstreams/36b0e83f-62e1-467f-a254-0fa1aef627fb/download
https://repositorio.uniandes.edu.co/bitstreams/8a37e765-b0ef-47eb-a0fb-6d7221cd2f4a/download
https://repositorio.uniandes.edu.co/bitstreams/66175dc8-6677-4fb9-a2f7-553d61cba73a/download
https://repositorio.uniandes.edu.co/bitstreams/14ab3836-96cc-43ba-836a-6c1013a83cf5/download
https://repositorio.uniandes.edu.co/bitstreams/60dc573b-b3b8-4a56-a5e9-11b64df2f862/download
https://repositorio.uniandes.edu.co/bitstreams/309f88e2-414e-43fd-86c4-c20fd46050b9/download
https://repositorio.uniandes.edu.co/bitstreams/2aee33ff-c59b-4696-8240-558f909462de/download
bitstream.checksum.fl_str_mv c903fe6825c7f88819444296b68e8019
b2e7d3289f7c0d11562e62acba56d5f3
0175ea4a2d4caec4bbcc37e300941108
ae9e573a68e7f92501b6913cc846c39f
fac5bbd1ec1d714d720dc488b0bfc035
10eb14c30d2e98de5280ce6daa9f933b
077fe7690a8c38c79cad71224fe9f5c5
d99dd6e6ccd7a400dc82c7e817e21279
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio institucional Séneca
repository.mail.fl_str_mv adminrepositorio@uniandes.edu.co
_version_ 1828159272975859712
spelling Takahashi Rodríguez, Silviavirtual::22368-1Campo Cotes, Santiago RafaelTakahashi Rodríguez, Silvia2025-01-22T16:04:16Z2025-01-22T16:04:16Z2025-01-21https://hdl.handle.net/1992/75569instname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/Bomberland is a modified clone of the popular arcade game Bomberman developed for an AI Agent Competition, adding a layer of cooperation using teams. This project aims to highlight how popular Deep Learning algorithms for game agents, Deep Q Learning and NEAT, perform against added complexity through cooperative, adversarial, and stochastic elements.Pregrado16 páginasapplication/pdfengUniversidad de los AndesIngeniería de Sistemas y ComputaciónFacultad de IngenieríaDepartamento de Ingeniería de Sistemas y ComputaciónAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Deep learning game agents in Bomberland: A comparative analysisTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/acceptedVersionhttp://purl.org/coar/resource_type/c_7a1fTexthttp://purl.org/redcol/resource_type/TPArtificial IntelligenceGame AgentsNEATMachine LearningIngenieríaBrockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., & Zaremba, W. (2016, June 6). OpenAI Gym. Retrieved from OpenAI: https://arxiv.org/abs/1606.01540Gymnasium Team. (2023). Gymnasium. Retrieved from Farama Foundation: https://gymnasium.farama.org/Krabbenhöft, H. N. (2022, May 12). Bomberland AI - Part I - Lingo, Replays and TensorFlow Observations. Retrieved from Hajos Personal Blog: https://hajo.me/blog/2022/05/12/coder-one-bomberland-tutorial-1of3-introduction-replays-and-conversion-to-tensorflow/MacWha, R. (2021, March 3). Evolving AIs using a NEAT algorithm. Retrieved from Medium: https://macwha.medium.com/evolving-ais-using-a-neat-algorithm-2d154c623828Mnih, V., Kavukcuouglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., . . . Antonoglou, I. (2015). Human-level control through deep reinforcement learning. Nature 518, 529-542.OpenAI Five Team. (2018, June 25). OpenAI Five. Retrieved from OpenAI: https://openai.com/research/openai-fiveOrkin, J. (2006). Three States and a Plan: The A.I. of F.E.A.R. Game Developers Conference.Stanley, K. O., & Miikulainen, R. (2002). Evolving Neural Networks through Augmenting Topologies. Evolutionary Computation 10(2), 99-127.TF-Agents Authors. (2023). Introduction to RL and Deep Q Networks. Retrieved from Tensorflow: https://www.tensorflow.org/agents/tutorials/0_intro_rlThe Interactive Agent Team. (2022, November 23). Building Interactive Agents in Video Game Worlds. Retrieved from Google Deepmind: https://deepmind.google/discover/blog/building-interactive-agents-in-video-game-worlds/Zhang, J. (2021, November 29). Bomberland. Retrieved from CoderOne: https://www.gocoder.one/blog/bomberland-multi-agent-artificial-intelligence-competition/201921995Publicationhttps://scholar.google.es/citations?user=x7gjZ04AAAAJvirtual::22368-10000-0001-7971-8979virtual::22368-1https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000143898virtual::22368-17ab9a4e1-60f0-4e06-936b-39f2bf93d8a0virtual::22368-17ab9a4e1-60f0-4e06-936b-39f2bf93d8a0virtual::22368-1ORIGINALDeep Learning Game Agents in Bomberland.pdfDeep Learning Game Agents in Bomberland.pdfapplication/pdf832058https://repositorio.uniandes.edu.co/bitstreams/6dc8a210-14e1-41bc-8fb7-cc727f7964fa/downloadc903fe6825c7f88819444296b68e8019MD51FormatoAutorización.pdfFormatoAutorización.pdfHIDEapplication/pdf296919https://repositorio.uniandes.edu.co/bitstreams/36b0e83f-62e1-467f-a254-0fa1aef627fb/downloadb2e7d3289f7c0d11562e62acba56d5f3MD54CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8908https://repositorio.uniandes.edu.co/bitstreams/8a37e765-b0ef-47eb-a0fb-6d7221cd2f4a/download0175ea4a2d4caec4bbcc37e300941108MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82535https://repositorio.uniandes.edu.co/bitstreams/66175dc8-6677-4fb9-a2f7-553d61cba73a/downloadae9e573a68e7f92501b6913cc846c39fMD53TEXTDeep Learning Game Agents in Bomberland.pdf.txtDeep Learning Game Agents in Bomberland.pdf.txtExtracted texttext/plain27678https://repositorio.uniandes.edu.co/bitstreams/14ab3836-96cc-43ba-836a-6c1013a83cf5/downloadfac5bbd1ec1d714d720dc488b0bfc035MD55FormatoAutorización.pdf.txtFormatoAutorización.pdf.txtExtracted texttext/plain1974https://repositorio.uniandes.edu.co/bitstreams/60dc573b-b3b8-4a56-a5e9-11b64df2f862/download10eb14c30d2e98de5280ce6daa9f933bMD57THUMBNAILDeep Learning Game Agents in Bomberland.pdf.jpgDeep Learning Game Agents in Bomberland.pdf.jpgGenerated Thumbnailimage/jpeg7064https://repositorio.uniandes.edu.co/bitstreams/309f88e2-414e-43fd-86c4-c20fd46050b9/download077fe7690a8c38c79cad71224fe9f5c5MD56FormatoAutorización.pdf.jpgFormatoAutorización.pdf.jpgGenerated Thumbnailimage/jpeg11490https://repositorio.uniandes.edu.co/bitstreams/2aee33ff-c59b-4696-8240-558f909462de/downloadd99dd6e6ccd7a400dc82c7e817e21279MD581992/75569oai:repositorio.uniandes.edu.co:1992/755692025-03-05 10:01:58.756http://creativecommons.org/licenses/by/4.0/Attribution 4.0 Internationalopen.accesshttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.coPGgzPjxzdHJvbmc+RGVzY2FyZ28gZGUgUmVzcG9uc2FiaWxpZGFkIC0gTGljZW5jaWEgZGUgQXV0b3JpemFjacOzbjwvc3Ryb25nPjwvaDM+CjxwPjxzdHJvbmc+UG9yIGZhdm9yIGxlZXIgYXRlbnRhbWVudGUgZXN0ZSBkb2N1bWVudG8gcXVlIHBlcm1pdGUgYWwgUmVwb3NpdG9yaW8gSW5zdGl0dWNpb25hbCBTw6luZWNhIHJlcHJvZHVjaXIgeSBkaXN0cmlidWlyIGxvcyByZWN1cnNvcyBkZSBpbmZvcm1hY2nDs24gZGVwb3NpdGFkb3MgbWVkaWFudGUgbGEgYXV0b3JpemFjacOzbiBkZSBsb3Mgc2lndWllbnRlcyB0w6lybWlub3M6PC9zdHJvbmc+PC9wPgo8cD5Db25jZWRhIGxhIGxpY2VuY2lhIGRlIGRlcMOzc2l0byBlc3TDoW5kYXIgc2VsZWNjaW9uYW5kbyBsYSBvcGNpw7NuIDxzdHJvbmc+J0FjZXB0YXIgbG9zIHTDqXJtaW5vcyBhbnRlcmlvcm1lbnRlIGRlc2NyaXRvcyc8L3N0cm9uZz4geSBjb250aW51YXIgZWwgcHJvY2VzbyBkZSBlbnbDrW8gbWVkaWFudGUgZWwgYm90w7NuIDxzdHJvbmc+J1NpZ3VpZW50ZScuPC9zdHJvbmc+PC9wPgo8aHI+CjxwPllvLCBlbiBtaSBjYWxpZGFkIGRlIGF1dG9yIGRlbCB0cmFiYWpvIGRlIHRlc2lzLCBtb25vZ3JhZsOtYSBvIHRyYWJham8gZGUgZ3JhZG8sIGhhZ28gZW50cmVnYSBkZWwgZWplbXBsYXIgcmVzcGVjdGl2byB5IGRlIHN1cyBhbmV4b3MgZGUgc2VyIGVsIGNhc28sIGVuIGZvcm1hdG8gZGlnaXRhbCB5L28gZWxlY3Ryw7NuaWNvIHkgYXV0b3Jpem8gYSBsYSBVbml2ZXJzaWRhZCBkZSBsb3MgQW5kZXMgcGFyYSBxdWUgcmVhbGljZSBsYSBwdWJsaWNhY2nDs24gZW4gZWwgU2lzdGVtYSBkZSBCaWJsaW90ZWNhcyBvIGVuIGN1YWxxdWllciBvdHJvIHNpc3RlbWEgbyBiYXNlIGRlIGRhdG9zIHByb3BpbyBvIGFqZW5vIGEgbGEgVW5pdmVyc2lkYWQgeSBwYXJhIHF1ZSBlbiBsb3MgdMOpcm1pbm9zIGVzdGFibGVjaWRvcyBlbiBsYSBMZXkgMjMgZGUgMTk4MiwgTGV5IDQ0IGRlIDE5OTMsIERlY2lzacOzbiBBbmRpbmEgMzUxIGRlIDE5OTMsIERlY3JldG8gNDYwIGRlIDE5OTUgeSBkZW3DoXMgbm9ybWFzIGdlbmVyYWxlcyBzb2JyZSBsYSBtYXRlcmlhLCB1dGlsaWNlIGVuIHRvZGFzIHN1cyBmb3JtYXMsIGxvcyBkZXJlY2hvcyBwYXRyaW1vbmlhbGVzIGRlIHJlcHJvZHVjY2nDs24sIGNvbXVuaWNhY2nDs24gcMO6YmxpY2EsIHRyYW5zZm9ybWFjacOzbiB5IGRpc3RyaWJ1Y2nDs24gKGFscXVpbGVyLCBwcsOpc3RhbW8gcMO6YmxpY28gZSBpbXBvcnRhY2nDs24pIHF1ZSBtZSBjb3JyZXNwb25kZW4gY29tbyBjcmVhZG9yIGRlIGxhIG9icmEgb2JqZXRvIGRlbCBwcmVzZW50ZSBkb2N1bWVudG8uPC9wPgo8cD5MYSBwcmVzZW50ZSBhdXRvcml6YWNpw7NuIHNlIGVtaXRlIGVuIGNhbGlkYWQgZGUgYXV0b3IgZGUgbGEgb2JyYSBvYmpldG8gZGVsIHByZXNlbnRlIGRvY3VtZW50byB5IG5vIGNvcnJlc3BvbmRlIGEgY2VzacOzbiBkZSBkZXJlY2hvcywgc2lubyBhIGxhIGF1dG9yaXphY2nDs24gZGUgdXNvIGFjYWTDqW1pY28gZGUgY29uZm9ybWlkYWQgY29uIGxvIGFudGVyaW9ybWVudGUgc2XDsWFsYWRvLiBMYSBwcmVzZW50ZSBhdXRvcml6YWNpw7NuIHNlIGhhY2UgZXh0ZW5zaXZhIG5vIHNvbG8gYSBsYXMgZmFjdWx0YWRlcyB5IGRlcmVjaG9zIGRlIHVzbyBzb2JyZSBsYSBvYnJhIGVuIGZvcm1hdG8gbyBzb3BvcnRlIG1hdGVyaWFsLCBzaW5vIHRhbWJpw6luIHBhcmEgZm9ybWF0byBlbGVjdHLDs25pY28sIHkgZW4gZ2VuZXJhbCBwYXJhIGN1YWxxdWllciBmb3JtYXRvIGNvbm9jaWRvIG8gcG9yIGNvbm9jZXIuPC9wPgo8cD5FbCBhdXRvciwgbWFuaWZpZXN0YSBxdWUgbGEgb2JyYSBvYmpldG8gZGUgbGEgcHJlc2VudGUgYXV0b3JpemFjacOzbiBlcyBvcmlnaW5hbCB5IGxhIHJlYWxpesOzIHNpbiB2aW9sYXIgbyB1c3VycGFyIGRlcmVjaG9zIGRlIGF1dG9yIGRlIHRlcmNlcm9zLCBwb3IgbG8gdGFudG8sIGxhIG9icmEgZXMgZGUgc3UgZXhjbHVzaXZhIGF1dG9yw61hIHkgdGllbmUgbGEgdGl0dWxhcmlkYWQgc29icmUgbGEgbWlzbWEuPC9wPgo8cD5FbiBjYXNvIGRlIHByZXNlbnRhcnNlIGN1YWxxdWllciByZWNsYW1hY2nDs24gbyBhY2Npw7NuIHBvciBwYXJ0ZSBkZSB1biB0ZXJjZXJvIGVuIGN1YW50byBhIGxvcyBkZXJlY2hvcyBkZSBhdXRvciBzb2JyZSBsYSBvYnJhIGVuIGN1ZXN0acOzbiwgZWwgYXV0b3IgYXN1bWlyw6EgdG9kYSBsYSByZXNwb25zYWJpbGlkYWQsIHkgc2FsZHLDoSBkZSBkZWZlbnNhIGRlIGxvcyBkZXJlY2hvcyBhcXXDrSBhdXRvcml6YWRvcywgcGFyYSB0b2RvcyBsb3MgZWZlY3RvcyBsYSBVbml2ZXJzaWRhZCBhY3TDumEgY29tbyB1biB0ZXJjZXJvIGRlIGJ1ZW5hIGZlLjwvcD4KPHA+U2kgdGllbmUgYWxndW5hIGR1ZGEgc29icmUgbGEgbGljZW5jaWEsIHBvciBmYXZvciwgY29udGFjdGUgY29uIGVsIDxhIGhyZWY9Im1haWx0bzpiaWJsaW90ZWNhQHVuaWFuZGVzLmVkdS5jbyIgdGFyZ2V0PSJfYmxhbmsiPkFkbWluaXN0cmFkb3IgZGVsIFNpc3RlbWEuPC9hPjwvcD4K