Generalized value iteration for discounted optimal control with stability analysis.
Mingming HaDing WangDerong LiuPublished in: Syst. Control. Lett. (2021)
Keyphrases
- optimal control
- stability analysis
- infinite horizon
- dynamic programming
- optimal control problems
- nonlinear systems
- markov decision processes
- control law
- finite horizon
- control problems
- markov decision process
- reinforcement learning
- feedback control
- policy iteration
- average cost
- production planning
- risk sensitive
- control strategy
- optimal policy
- lyapunov function
- real time
- multistage
- sliding mode
- linear quadratic
- average reward
- state space
- adaptive control
- mathematical model
- search space
- neural network