A closed-loop saddle point for zero-sum linear-quadratic stochastic differential games with mean-field type.
Ran TianZhiyong YuRucheng ZhangPublished in: Syst. Control. Lett. (2020)
Keyphrases
- closed loop
- linear quadratic
- game theory
- control system
- control scheme
- markov networks
- optimal control
- gaussian model
- nash equilibrium
- dynamical systems
- markov random field
- pid controller
- vector valued
- feature selection
- bayesian inference
- reinforcement learning
- maximum margin
- multiscale
- pairwise
- posterior distribution