Exploiting homogeneity for the optimal control of discrete-time systems: application to value iteration.
Mathieu GranzottoRomain PostoyanLucian BusoniuDragan NesicJamal DaafouzPublished in: CDC (2021)
Keyphrases
- optimal control
- optimal control problems
- dynamic programming
- infinite horizon
- control strategy
- control problems
- brownian motion
- markov decision processes
- data mining
- feedback control
- markov chain
- control law
- finite state
- policy iteration
- lyapunov function
- risk sensitive
- stochastic control
- linear quadratic
- reinforcement learning