Listar Computación por tema "System optimal"
Mostrando ítems 1-1 de 1
-
Regret minimisation and system-efficiency in route choice
(2018) [Tesis]Multiagent reinforcement learning (MARL) is a challenging task, where self-interested agents concurrently learn a policy that maximise their utilities. Learning here is difficult because agents must adapt to each other, ...