Login / Signup
Optimality Conditions for Long-Run Average Rewards With Underselectivity and Nonsmooth Features.
Xi-Ren Cao
Published in:
IEEE Trans. Autom. Control. (2017)
Keyphrases
</>
long run
optimality conditions
average cost
short run
nonlinear programming
newton method
feature space
feature set
bilevel programming
control policy
machine learning
classification models
learning models