No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization.

Martino Bernasconi Matteo Castiglioni Andrea Celli

Published in: CoRR (2024)

Keyphrases

regret minimization
special case
nash equilibrium
game theoretic
constraint satisfaction
regret bounds
learning algorithm
online learning
constrained optimization
multi armed bandit problems