Finite-horizon dynamic games for a class of nonlinear stochastic systems.

Hiroaki Mukaidani Hua Xu Vasile Dragan Toru Yamamoto

Published in: CDC (2015)

Keyphrases

finite horizon
stochastic systems
infinite horizon
stochastic models
markov decision processes
optimal policy
confidence intervals
average cost
search algorithm
probabilistic model
non stationary
sample size
single item