Login / Signup
A distributed adaptive steplength stochastic approximation method for monotone stochastic Nash Games.
Farzad Yousefian
Angelia Nedic
Uday V. Shanbhag
Published in:
ACC (2013)
Keyphrases
</>
stochastic approximation
dynamic programming
cost function
machine learning
computational complexity
monte carlo
reinforcement learning
search algorithm
lower bound
support vector machine
graphical models
game theoretic