Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games.
Kaiqing ZhangZhuoran YangTamer BasarPublished in: NeurIPS (2019)
Keyphrases
- nash equilibria
- stochastic games
- game theory
- incomplete information
- fictitious play
- nash equilibrium
- game theoretic
- linear quadratic
- pure strategy
- solution concepts
- optimal solution
- optimal control
- multiagent learning
- vector valued
- closed loop
- congestion games
- boolean games
- machine learning
- optimal policy
- cooperative
- learning algorithm