Search research articles

ACERCA DE JoVE

Visión General Liderazgo Blog Centro de Ayuda JoVE

AUTORES

Proceso de Publicación Consejo Editorial Alcance y Políticas Revisión por Pares Preguntas Frecuentes Enviar

BIBLIOTECARIOS

Testimonios Suscripciones Acceso Recursos Consejo Asesor de Bibliotecas Preguntas Frecuentes

INVESTIGACIÓN

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archivo

EDUCACIÓN

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Centro de Recursos para Profesores Sitio de Profesores

Términos y Condiciones de Uso

Política de Privacidad

Videos de Conceptos Relacionados

Reinforcement

Reinforcement

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:

Observational Learning

Observational Learning

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...

Reinforcement Schedules

Reinforcement Schedules

Positive reinforcement is a powerful method for teaching new behaviors to both animals and humans. B.F. Skinner demonstrated this with his experiments using rats in a Skinner box. When a rat pressed a lever, it received a food pellet. This immediate reward encouraged the rat to repeat the behavior. This method, where a reward follows every instance of the behavior, is known as continuous reinforcement. It is highly effective for establishing new behaviors quickly.
Once a behavior is learned,...

Avoidance Learning and Learned Helplessness

Avoidance Learning and Learned Helplessness

Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

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...

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por

Same author

Participant lived experiences of high-intensity interval training in UK cardiac rehabilitation (HIIT or MISS UK): A qualitative study.

PloS one·2026

Same author

Accelerating scientific discovery with Co-Scientist.

Nature·2026

Same author

Identifying clinical phenotypes of injured patients who meet Air Medical Prehospital Triage (AMPT) score criteria for helicopter transport.

The journal of trauma and acute care surgery·2026

Same author

Open surgery appears to be the preferred treatment in patients with nutcracker syndrome: A vascular low frequency disease consortium analysis.

Journal of vascular surgery. Venous and lymphatic disorders·2026

Same author

From ChatGPT to UroGPT: A guideline-trained artificial intelligence model for male infertility.

Current urology·2026

Same author

The Time Is Now: Barriers and Solutions for an ACGME Requirement in Reproductive Psychiatry.

Academic psychiatry : the journal of the American Association of Directors of Psychiatric Residency Training and the Association for Academic Psychiatry·2026

Search research articles

Video Experimental Relacionado

Updated: Jan 4, 2026

Study Motor Skill Learning by Single-pellet Reaching Tasks in Mice

Study Motor Skill Learning by Single-pellet Reaching Tasks in Mice

Published on: March 4, 2014

Nivel de Gran Maestro en StarCraft II utilizando el aprendizaje de refuerzo multi-agente

Oriol Vinyals¹, Igor Babuschkin², Wojciech M Czarnecki²

¹DeepMind, London, UK. vinyals@google.com.

|November 1, 2019

Resumen

Este resumen es generado por máquina.

AlphaStar, un agente de inteligencia artificial, alcanzó el nivel de Gran Maestro en StarCraft II mediante el uso de aprendizaje de refuerzo multi-agente. Esta IA demuestra capacidades avanzadas en juegos complejos de estrategia del mundo real.

Más Videos Relacionados

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice

Published on: March 3, 2023

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

Videos de Experimentos Relacionados

Last Updated: Jan 4, 2026

Study Motor Skill Learning by Single-pellet Reaching Tasks in Mice

Study Motor Skill Learning by Single-pellet Reaching Tasks in Mice

Published on: March 4, 2014

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice

Published on: March 3, 2023

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

Área de la Ciencia:

Inteligencia artificial
Teoría de juegos computacionales
Sistemas de agentes múltiples

Sus antecedentes:

StarCraft presenta desafíos complejos de múltiples agentes relevantes para las aplicaciones del mundo real.
Los agentes anteriores de IA en StarCraft han confiado en la simplificación del juego o habilidades sobrehumanas.
Ninguna IA anterior ha igualado la habilidad general de los mejores jugadores humanos de StarCraft.

Objetivo del estudio:

Desarrollar un agente de IA capaz de competir a un nivel humano superior en el complejo juego de estrategia en tiempo real StarCraft II.
Utilizar métodos de aprendizaje de propósito general aplicables a otros ámbitos difíciles.

Principales métodos:

Empleado un algoritmo de aprendizaje de refuerzo multi-agente.
Utilizó una liga diversa de redes neuronales profundas con estrategias adaptativas y contraestrategias.
Entrenado en los datos de los juegos de humanos y agentes en StarCraft II.

Principales resultados:

El agente AlphaStar alcanzó el nivel de Gran Maestro en las tres carreras de StarCraft II.
El rendimiento de AlphaStar superó al 99.8% de los jugadores humanos clasificados.
Demostró un avance significativo en las capacidades de IA para juegos de estrategia complejos.

Conclusiones:

Los métodos de aprendizaje de propósito general, particularmente el aprendizaje de refuerzo multi-agente, pueden lograr un rendimiento a nivel humano en entornos estratégicos complejos como StarCraft II.
AlphaStar representa un hito importante en la investigación de inteligencia artificial para juegos de estrategia en tiempo real.
El enfoque puede extenderse a otros ámbitos que requieren una toma de decisiones y una coordinación complejas.