Linear-quadratic optimal control for partially observed forward-backward stochastic systems with random jumps.
Tian ChenGuangchen WangZhen WuPublished in: Sci. China Inf. Sci. (2022)
Keyphrases
- optimal control
- partially observed
- linear quadratic
- forward backward
- stochastic systems
- hidden markov models
- dynamic programming
- stochastic models
- closed loop
- control strategy
- confidence intervals
- infinite horizon
- reinforcement learning
- control law
- markov chain
- dynamical systems
- real time
- gaussian model
- vector valued