A state-space parametrization of discrete-time two-degree-of-freedom integral controllers.
Hai-Jiao GuoTadashi IshiharaHiroshi TakedaPublished in: Autom. (1994)
Keyphrases
- state space
- markov chain
- reinforcement learning
- heuristic search
- state variables
- dynamic programming
- control system
- finite state
- dynamical systems
- markov decision processes
- reinforcement learning algorithms
- optimal policy
- goal state
- state transition
- evolutionary robotics
- power law
- control law
- control strategy
- objective function