Optimal Control by Direct Approximation of the Gradient of the Cost-to-Go.
Douglas B. TweedPublished in: Control. Intell. Syst. (2013)
Keyphrases
- optimal control
- average cost
- dynamic programming
- control problems
- infinite horizon
- policy gradient
- feedback control
- control strategy
- risk sensitive
- class of nonlinear systems
- optimal control problems
- fixed cost
- reinforcement learning
- brownian motion
- control law
- piecewise constant
- lyapunov function
- real time
- total cost
- markov decision processes
- edge detection
- neural network
- stochastic control
- linear quadratic