The maximum principle for partially observed optimal control of forward-backward stochastic systems with random jumps.
Hua XiaoPublished in: J. Syst. Sci. Complex. (2011)
Keyphrases
- optimal control
- partially observed
- forward backward
- stochastic systems
- control problems
- sample path
- hidden markov models
- dynamic programming
- stochastic models
- markov chain
- policy iteration
- control strategy
- reinforcement learning
- confidence intervals
- infinite horizon
- control law
- asymptotic analysis
- heavy tailed
- mathematical model
- state space
- probability distribution
- machine learning