Rotting bandits are no harder than stochastic ones.

Julien Seznec Andrea Locatelli Alexandra Carpentier Alessandro Lazaric Michal Valko

Published in: AISTATS (2019)

Keyphrases

stochastic systems
stochastic models
np hard
stochastic nature
multi armed bandit
regret bounds
reinforcement learning
np complete
stochastic optimization
stochastic model
case study
monte carlo
lower bound
database
clustering algorithm
web services
information retrieval
data mining
real world
neural network
real time