Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound.
Xiaofeng LinNuyun CaoYuzhang LinPublished in: ADPRL (2013)
Keyphrases
- optimal control
- class of nonlinear systems
- dynamic programming
- error bounds
- state space
- feedback control
- control problems
- infinite horizon
- control strategy
- optimal control problems
- control law
- linear programming
- worst case
- reinforcement learning
- finite sample
- theoretical analysis
- adaptive control
- knapsack problem
- lyapunov function
- stochastic control
- real time
- np hard
- control algorithm
- closed loop