Data-Driven Policy Iteration for Nonlinear Optimal Control Problems.
Corrado PossieriMario SassanoPublished in: IEEE Trans. Neural Networks Learn. Syst. (2023)
Keyphrases
- policy iteration
- optimal control
- optimal control problems
- markov decision processes
- infinite horizon
- solving nonlinear
- reinforcement learning
- production planning
- model free
- dynamic programming
- control strategy
- fixed point
- least squares
- nonlinear equations
- markov decision process
- optimal policy
- temporal difference
- control law
- average cost
- linear programming
- finite state
- closed loop
- multistage
- objective function
- neural network
- convergence rate
- control theory
- decision making