Equilibrium Bandits: Learning Optimal Equilibria of Unknown Dynamics.

Siddharth Chandak Ilai Bistritz Nicholas Bambos

Published in: CoRR (2023)

Keyphrases

learning algorithm
learning process
supervised learning
fixed point
dynamic programming
unsupervised learning
learning tasks
learning problems
nash equilibrium
data sets
cooperative
learning systems
game theory
optimal control
long run