Model-free optimal control design for a class of linear discrete-time systems with multiple delays using adaptive dynamic programming.
Jilie ZhangHuaguang ZhangYanhong LuoTao FengPublished in: Neurocomputing (2014)
Keyphrases
- optimal control
- dynamic programming
- model free
- reinforcement learning
- linear quadratic
- risk sensitive
- optimal control problems
- control problems
- infinite horizon
- impedance control
- feedback control
- rl algorithms
- policy iteration
- control strategy
- state space
- reinforcement learning algorithms
- linear systems
- function approximation
- least squares
- finite state
- optimal policy
- machine learning algorithms