Login / Signup
Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descent.
Ian M. Gemp
Rahul Savani
Marc Lanctot
Yoram Bachrach
Thomas W. Anthony
Richard Everett
Andrea Tacchetti
Tom Eccles
János Kramár
Published in:
AAMAS (2022)
Keyphrases
</>
cost function
objective function
closed form
sample size
game theory
small sample
approximation error
sample set
error bounds
nash equilibrium
approximation schemes
sample points
relative error
nash equilibria
approximation algorithms
incomplete information
loss function