Continuous Aggregative LQG Games with Delayed Discrete Observations
For researchers in multi-agent systems and mean field games, this work addresses the realistic scenario of delayed and discrete population-level information, extending theoretical foundations to more practical settings.
This paper characterizes agent best responses in mean field LQG games where agents observe the empirical mean state with delay at discrete times, provides sufficient conditions for Nash equilibrium existence in finite populations, and quantifies the cost increase due to delayed discrete observations compared to zero-latency discrete or continuous observations.
Mean field game equilibria are predicated on the assumption of immediate pairwise interactions within a population of homogeneous agents with asymptotically vanishing influence as population size increases. However, in many real-world cases, agents receive population-level information with a delay. In this paper, we characterize agent best responses under an information exchange structure whereby agents observe the empirical mean state only at discrete time instants with some delay. Sufficient conditions are presented for the existence of a Nash equilibrium within a finite population of agents, and the cost increase due to delayed discrete empirical mean observations relative to zero-latency discrete observations and continuous global-state observations is also evaluated.