Integral Q-learning and explorized policy iteration for adaptive optimal control of continuous-time linear systems.
Jae Young LeeJin Bae ParkYoon Ho ChoiPublished in: Autom. (2012)
Keyphrases
- optimal control
- policy iteration
- linear systems
- infinite horizon
- dynamic programming
- actor critic
- reinforcement learning
- control problems
- dynamical systems
- approximate dynamic programming
- sufficient conditions
- optimal control problems
- policy evaluation
- markov decision processes
- control strategy
- model free
- optimal policy
- markov decision problems
- control theory
- discounted reward
- neural network
- average reward
- real time
- artificial neural networks
- markov decision process
- genetic algorithm
- state space
- average cost
- function approximation