Nash Regret Guarantees for Linear Bandits.

Ayush Sawarni Soumybrata Pal Siddharth Barman

Published in: CoRR (2023)

Keyphrases

regret bounds
multi armed bandits
game theory
multi armed bandit problems
online learning
lower bound
linear systems
nash equilibrium
evolutionary algorithm
linear regression
decision making
quadratic programming
nash equilibria
closed form
expert advice
weighted majority
bandit problems
bayesian networks