Adaptive dynamic programming-based optimal control of unknown nonaffine nonlinear discrete-time systems with proof of convergence.
Xin ZhangHuaguang ZhangQiuye SunYanhong LuoPublished in: Neurocomputing (2012)
Keyphrases
- optimal control
- dynamic programming
- linear quadratic
- class of nonlinear systems
- optimal control problems
- control problems
- feedback control
- risk sensitive
- lyapunov function
- infinite horizon
- machine learning
- control strategy
- brownian motion
- control law
- real time
- control system
- linear systems
- reinforcement learning
- knapsack problem
- convergence rate
- markov decision processes
- linear programming
- state space