Coupling Policy Iterations with Piecewise Quadratic Lyapunov Functions.
Assalé AdjéPublished in: HSCC (2017)
Keyphrases
- dynamical systems
- penalty functions
- pairwise
- neural network
- objective function
- optimal policy
- basis functions
- closed loop
- stability analysis
- nonlinear systems
- nonlinear functions
- cubic spline interpolation
- linear functions
- control theory
- asymptotically optimal
- adaptive control
- fuzzy model
- linear programming
- optimal solution
- reinforcement learning
- genetic algorithm