Model-free H∞ stochastic optimal design for unknown linear networked control system zero-sum games via Q-learning.
Hao XuSarangapani JagannathanPublished in: ISIC (2011)
Keyphrases
- model free
- optimal design
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- networked control systems
- policy iteration
- temporal difference
- linear systems
- control theory
- reinforcement learning methods
- pid controller
- linear model
- path planning
- monte carlo
- average reward
- rl algorithms
- genetic algorithm