Collaborative AI in the Geometry Friends Game Competition

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 cooperat...

ver descrição completa

Detalhes bibliográficos
Autores: Almagro, Alberto, Llamas-Núñez, Juan Carlos, Sánchez Ruiz-Granados, Antonio Alejandro, Díaz Agudo, María Belén
Formato: artículo
Fecha de publicación:2024
País:España
Recursos:Universidad Complutense de Madrid (UCM)
Repositorio:Docta Complutense
Idioma:inglés
OAI Identifier:oai:docta.ucm.es:20.500.14352/121893
Acesso em linha:https://hdl.handle.net/20.500.14352/121893
Access Level:acceso abierto
Palavra-chave:Collaborative agents
Geometry Friends
Symbolic AI
Action planning
Reinforcement Learning
Inteligencia artificial (Informática)
1203.04 Inteligencia Artificial
Descrição
Resumo: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.