Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games.
Zuyue FuZhuoran YangYongxin ChenZhaoran WangPublished in: CoRR (2019)
Keyphrases
- nash equilibria
- optimal control
- actor critic
- linear quadratic
- incomplete information
- game theory
- stochastic games
- policy gradient
- nash equilibrium
- dynamic programming
- game theoretic
- reinforcement learning
- dynamical systems
- markov random field
- pure strategy
- control strategy
- em algorithm
- mixed strategy
- worst case
- policy iteration
- neuro fuzzy
- objective function
- temporal difference
- closed loop
- multi agent systems