Reinforcement Learning in Nonzero-sum Linear Quadratic Deep Structured Games: Global Convergence of Policy Optimization.
Masoud RoudneshinJalal ArabneydiAmir G. AghdamPublished in: CoRR (2020)
Keyphrases
- global convergence
- reinforcement learning
- optimization methods
- convergence speed
- global optimum
- optimal policy
- convergence analysis
- convergence rate
- linear quadratic
- optimal control
- line search
- convex minimization
- closed loop
- particle swarm optimization algorithm
- objective function
- globally convergent
- optimization algorithm
- machine learning
- particle swarm
- function approximators
- state space
- cost function
- vector valued
- optimization method
- differential evolution