Adaptive dynamic programming for discrete-time linear quadratic regulation based on multirate generalised policy iteration.
Tae Yoon ChunJae Young LeeJin Bae ParkYoon Ho ChoiPublished in: Int. J. Control (2018)
Keyphrases
- linear quadratic
- optimal control
- policy iteration
- dynamic programming
- markov decision processes
- infinite horizon
- optimal policy
- finite state
- reinforcement learning
- markov decision problems
- control strategy
- linear programming
- average reward
- state space
- closed loop
- dynamical systems
- stereo matching
- vector valued
- average cost
- fixed point
- model free
- temporal difference
- gaussian model
- subband
- filter bank
- wavelet transform
- kernel methods