An alpha derivative formulation of the Hamilton-Jacobi-Bellman equation Of Dynamic Programming.
John SeifferttPublished in: IJCNN (2009)
Keyphrases
- hamilton jacobi bellman
- optimal control
- dynamic programming
- control problems
- approximate dynamic programming
- stochastic control
- state space
- nonlinear systems
- infinite horizon
- reinforcement learning
- control law
- linear programming
- control strategy
- linear program
- brownian motion
- optimal policy
- markov chain
- machine learning
- dynamical systems
- multiscale