Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path. (arXiv:2208.11639v2 [cs.LG] UPDATED)

We consider online reinforcement learning in Mean-Field Games. In contrast to
the existing works, we alleviate the need for a mean-field oracle by developing
an algorithm that estimates the mean-field and the optimal policy using a
single sample path of the generic agent. We call this Sandbox Learning, as it
can be used as a warm-start for any agent operating in a multi-agent
non-cooperative setting. We adopt a two timescale approach in which an online
fixed-point recursion for the mean-field …

arxiv free games learning lg mean oracle path reinforcement reinforcement learning