Scalable Deep Reinforcement Learning Algorithms for Mean Field Games. (arXiv:2203.11973v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2203.11973

Mean Field Games (MFGs) have been introduced to efficiently approximate games
with very large populations of strategic agents. Recently, the question of
learning equilibria in MFGs has gained momentum, particularly using model-free
reinforcement learning (RL) methods. One limiting factor to further scale up
using RL is that existing algorithms to solve MFGs require the mixing of
approximated quantities such as strategies or $q$-values. This is far from
being trivial in the case of non-linear function approximation that enjoy good
generalization …

algorithms arxiv deep games learning lg mean reinforcement reinforcement learning scalable