Function approximation for the deterministic Hamilton-Jacobi-Bellman equation.
Matthias RunggerOlaf StursbergPublished in: CDC (2009)
Keyphrases
- function approximation
- hamilton jacobi bellman
- reinforcement learning
- control problems
- optimal control
- nonlinear systems
- approximate dynamic programming
- stochastic control
- dynamical systems
- learning tasks
- radial basis function
- temporal difference learning
- model free
- temporal difference
- queueing systems
- adaptive control
- markov decision processes
- state space
- hamilton jacobi
- reinforcement learning algorithms
- function approximators
- control law
- control strategy
- learning problems
- neural network