Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games.
Zuyue FuZhuoran YangYongxin ChenZhaoran WangPublished in: ICLR (2020)
Keyphrases
- nash equilibria
- optimal control
- actor critic
- linear quadratic
- game theory
- incomplete information
- stochastic games
- dynamic programming
- policy gradient
- game theoretic
- nash equilibrium
- reinforcement learning
- pure strategy
- control strategy
- dynamical systems
- closed loop
- markov random field
- em algorithm
- infinite horizon
- policy iteration
- worst case
- cooperative
- neuro fuzzy
- function approximation
- resource allocation
- monte carlo
- learning algorithm