Reinforcement Learning in Linear Quadratic Deep Structured Teams: Global Convergence of Policy Gradient Methods.
Vida FathiJalal ArabneydiAmir G. AghdamPublished in: CDC (2020)
Keyphrases
- global convergence
- policy gradient methods
- linear quadratic
- optimal control
- reinforcement learning
- actor critic
- policy gradient
- natural actor critic
- global optimum
- convergence speed
- convergence rate
- optimization methods
- robot arm
- closed loop
- function approximators
- dynamical systems
- dynamic programming
- function approximation
- vector valued
- reinforcement learning algorithms
- multi agent
- gradient method
- particle swarm
- optimization method
- simulated annealing
- optimal policy
- markov decision processes
- neural network
- reinforcement learning methods
- state space
- reinforcement learning problems
- hybrid algorithm
- learning algorithm