Stochastic Bandits with Delay-Dependent Payoffs.

Leonardo Cella Nicolò Cesa-Bianchi

Published in: CoRR (2019)

Keyphrases

delay dependent
lyapunov krasovskii functional
stochastic systems
asymptotic stability
exponential stability
robust stability
closed loop supply chain
stability criterion
sufficient conditions
hopfield neural network
closed loop
reinforcement learning
regret bounds