Collaborative AI in the Geometry Friends Game Competition
dc.contributor.author | Almagro, Alberto | |
dc.contributor.author | Llamas-Núñez, Juan Carlos | |
dc.contributor.author | Sánchez Ruiz-Granados, Antonio Alejandro | |
dc.contributor.author | Díaz Agudo, María Belén | |
dc.date.accessioned | 2025-06-26T13:41:12Z | |
dc.date.available | 2025-06-26T13:41:12Z | |
dc.date.issued | 2024-10-29 | |
dc.description.abstract | Geometry Friends is a collaborative platform game featuring two agents, a circle and a rectangle, navigating through physics-driven levels to collect diamonds. Each level presents challenges in the form of obstacles and diamonds arranged in different configurations that forces the agents to cooperate. In this article, we describe the Universidad Complutense de Madrid (UCM) agents, that participated in the 2023 Geometry Friends AI Competition with excellent results, especially in the collaborative track. Our approach combines level analysis, motion simulation, abstract planning, scripted actions, reinforcement learning, and different types of agent interaction. The contributions are versatile and potentially applicable to other collaborative platform games. | |
dc.description.department | Depto. de Ingeniería de Software e Inteligencia Artificial (ISIA) | |
dc.description.faculty | Fac. de Informática | |
dc.description.refereed | TRUE | |
dc.description.sponsorship | Spanish Committee of Science and Innovation | |
dc.description.sponsorship | Universidad Complutense de Madrid | |
dc.description.status | pub | |
dc.identifier.doi | 10.1109/TG.2024.3487309 | |
dc.identifier.officialurl | https://doi.org/10.1109/TG.2024.3487309 | |
dc.identifier.uri | https://hdl.handle.net/20.500.14352/121893 | |
dc.issue.number | 2 | |
dc.journal.title | IEEE Transactions on Games | |
dc.language.iso | eng | |
dc.page.final | 418 | |
dc.page.initial | 408 | |
dc.publisher | IEEE | |
dc.relation.projectID | PID2023-150566OB-I00 | |
dc.relation.projectID | PID2021-123368OB-I00 | |
dc.rights | Attribution 4.0 International | en |
dc.rights.accessRights | open access | |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
dc.subject.keyword | Collaborative agents | |
dc.subject.keyword | Geometry Friends | |
dc.subject.keyword | Symbolic AI | |
dc.subject.keyword | Action planning | |
dc.subject.keyword | Reinforcement Learning | |
dc.subject.ucm | Inteligencia artificial (Informática) | |
dc.subject.unesco | 1203.04 Inteligencia Artificial | |
dc.title | Collaborative AI in the Geometry Friends Game Competition | |
dc.type | journal article | |
dc.type.hasVersion | VoR | |
dc.volume.number | 17 | |
dspace.entity.type | Publication | |
relation.isAuthorOfPublication | 90c1631c-e546-4b8e-b5f2-c12ab516957c | |
relation.isAuthorOfPublication | 95de81bf-4637-4307-8ff6-f2c06c591d18 | |
relation.isAuthorOfPublication.latestForDiscovery | 90c1631c-e546-4b8e-b5f2-c12ab516957c |
Download
Original bundle
1 - 1 of 1
Loading...
- Name:
- Collaborative_AI_in_the_Geometry_Friends_Game_Competition.pdf
- Size:
- 2.77 MB
- Format:
- Adobe Portable Document Format