Sign in
An Interior-Point Differentiable Path-Following Method to Compute Stationary Equilibria in Stochastic Games.
Chuangyin Dang
P. Jean-Jacques Herings
Peixuan Li
Published in:
INFORMS J. Comput. (2022)
Keyphrases
</>
stochastic games
reinforcement learning
search algorithm
support vector machine
objective function
dynamic programming
nash equilibria
interior point
markov random field
training samples
kernel function
incomplete information
convergence rate