Stability and monotone convergence of generalised policy iteration for discrete-time linear quadratic regulations.
Tae Yoon ChunJae Young LeeJin Bae ParkYoon Ho ChoiPublished in: Int. J. Control (2016)
Keyphrases
- linear quadratic
- policy iteration
- optimal control
- convergence rate
- markov decision processes
- dynamical systems
- vector valued
- infinite horizon
- fixed point
- closed loop
- reinforcement learning
- dynamic programming
- model free
- finite state
- average reward
- least squares
- markov decision process
- optimal policy
- control strategy
- temporal difference
- convergence speed
- gaussian model
- average cost
- neural network
- linear programming
- state space
- step size
- markov chain
- computer vision