Multi-Agent Reinforcement Learning: Foundations and Modern Approaches

El Instituto de Investigación en Inteligencia Artificial (IIIA-CSIC) organiza este curso impartido por el investigador Stefano V. Albrecht, investigador en la Universidad de Edimburgo, especializado en aprendizaje por refuerzo y sistemas multiagente. El curso lleva por título: Multi-Agent Reinforcement Learning: Foundations and Modern Approaches y se impartirá en inglés. El registro es de pago y se ofrecen descuentos y becas para estudiantes. 

El curso se celebrará de manera presencial y online. 

Información del curso:

Multi-Agent Reinforcement Learning (MARL), an area of machine learning in which a collective of agents learn to optimally interact in a shared environment, boasts a growing array of applications in modern life, from autonomous driving and multi-robot factories to automated trading and energy network management. This course provides an introduction to the models, solution concepts, algorithmic ideas, technical challenges, and modern approaches in MARL. The course first introduces the field's foundations, including basics of reinforcement learning theory and algorithms, interactive game models, different solution concepts for games, and the algorithmic ideas underpinning MARL research. It then details contemporary MARL algorithms which leverage deep learning techniques, covering ideas such as centralized training with decentralized execution, value decomposition, parameter sharing, and self-play. The course follows the new MIT Press textbook of the course lecturer available for free at www.marl-book.com.

Información y registro a través de la página web: https://iiia.csic.es/en-us/marl-course.