Keyphrases
Nash Equilibrium
100%
Policy Optimization
100%
Zero-sum Linear Quadratic Differential Game
100%
Non-convexity
40%
Linear-quadratic Games
40%
Nonconvex
20%
Convergence Property
20%
Gradient Method
20%
Theoretical Aspects
20%
Stationary Point
20%
Optimization Methods
20%
Saddle Point Problem
20%
Linear Feedback Control
20%
Locally Linear
20%
Reinforcement Learning Algorithm
20%
Policy-based
20%
Global Convergence
20%
Control Policy
20%
Policy Space
20%
Nonconcave
20%
Linear Convergence
20%
Optimization Landscape
20%
Zero-sum Markov Game
20%
Computer Science
Nash Equilibrium
100%
Optimization Policy
100%
Objective Function
20%
Convergence Property
20%
Feedback Control
20%
Stationary Point
20%
Convergence Rate
20%
Reinforcement Learning
20%
Global Convergence
20%
Gradient Method
20%
Mathematics
Nash Equilibrium
100%
Convergence Property
20%
Convergence Rate
20%
Stationary Point
20%
Saddle Point
20%
Objective Function
20%
Feedback Control
20%
Linear Convergence
20%
Initial Step
20%
Economics, Econometrics and Finance