Reinforcement learning-based optimal control considering L computation time delay of linear discrete-time systems.
Taishi FujitaToshimitsu UshioPublished in: ADPRL (2014)
Keyphrases
- optimal control
- reinforcement learning
- linear quadratic
- optimal control problems
- control problems
- feedback control
- dynamic programming
- class of nonlinear systems
- control strategy
- brownian motion
- infinite horizon
- linear systems
- actor critic
- markov chain
- function approximation
- rl algorithms
- lyapunov function
- learning algorithm
- control law
- optimal policy