Video Experimental Relacionado
Updated: Jan 8, 2026
11:53
Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm
Published on: December 9, 2012
13.4K
Aprendizaje por refuerzo multiagente basado en grafos con población evolutiva para la cooperación
Kexing Peng1, Hanwen Qi1, Tinghuai Ma2
1School of Computer Science, Nanjing University of Information Science & Technology, Nanjing, 210044, China.
Resumen
Este estudio presenta GDE, un nuevo marco de aprendizaje por refuerzo multiagente (MARL) que mejora la coordinación en tareas complejas. GDE combina la descomposición de valor basada en grafos con la optimización de políticas evolutivas por etapas para mejorar el rendimiento del agente.
Área de la Ciencia:
- Inteligencia Artificial
- Robótica
- Ciencias de la Computación
Sus antecedentes:
- Los métodos existentes de aprendizaje por refuerzo multiagente (MARL) enfrentan desafíos en la escalabilidad a tareas de coordinación complejas debido a observaciones limitadas de los agentes e interacciones dinámicas.
- La convergencia a políticas óptimas es difícil a medida que aumenta la complejidad de la tarea y el espacio de políticas, lo que afecta las evaluaciones estables de las políticas.
Objetivo del estudio:
- Proponer GDE, un marco MARL diseñado para superar los problemas de escalabilidad y convergencia en sistemas multiagente cooperativos.
- Mejorar la coordinación de agentes y la propagación de información en entornos dinámicos sin requerir el consenso del estado.
Principales métodos:
- GDE integra la descomposición de valor basada en grafos con la optimización de políticas evolutivas por etapas.
- Se utilizan algoritmos evolutivos (EAs) para la búsqueda aleatoria sin gradiente para mejorar la exploración de políticas y la convergencia.
- Se emplean redes neuronales de grafos (GNN) para extender los campos receptivos de los agentes y facilitar la propagación de información, aprovechando la invarianza de permutación para una convergencia estable con datos dinámicos.
Principales resultados:
- GDE demuestra un rendimiento superior en tareas de coordinación complejas, incluida la microgestión de StarCraft II, la cooperación de robots MAMuJoCo y la conducción autónoma SUMO.
- El marco captura eficazmente la dinámica de coordinación compleja a través de la formación de equipos multiagente y las GNN.
- Los resultados experimentales validan la efectividad y necesidad de cada módulo dentro del marco GDE.
Conclusiones:
- GDE ofrece una solución robusta para mejorar la coordinación y la convergencia de políticas en MARL.
- La combinación propuesta de descomposición basada en grafos y optimización evolutiva es eficaz para sistemas multiagente complejos.
- El diseño modular y la adaptabilidad del marco lo hacen adecuado para diversas aplicaciones del mundo real.
Videos de Conceptos Relacionados
01:23Reinforcement
786
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
786
00:48Optimal Foraging
13.4K
How animals obtain and eat their food is called foraging behavior. Foraging can include searching for plants and hunting for prey and depends on the species and environment.
13.4K
01:12Observational Learning
791
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
791
01:06Collisions in Multiple Dimensions: Problem Solving
5.2K
In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
5.2K
02:54Evolutionary Relationships through Genome Comparisons
6.8K
Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
6.8K
01:22Multi-input and Multi-variable systems
373
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
In the absence of...
373