An optimal control problem in determining the optimal reinforcement schedules for the Lanchester equations.
Hsi-Mei ChenPublished in: Comput. Oper. Res. (2003)
Keyphrases
- optimal control
- reinforcement learning
- dynamic programming
- linear quadratic
- control problems
- infinite horizon
- control strategy
- feedback control
- risk sensitive
- average cost
- optimal control problems
- class of nonlinear systems
- brownian motion
- hamilton jacobi bellman
- stochastic control
- control law
- mathematical model
- lyapunov function
- scheduling problem