Best Arm Identification in Contaminated Stochastic Bandits.

Arpan Mukherjee Ali Tajer Pin-Yu Chen Payel Das

Published in: NeurIPS (2021)

Keyphrases

stochastic systems
stochastic optimization
multi armed bandit problems
real time
regret bounds
neural network
e learning
website
clustering algorithm
multi agent
evolutionary algorithm
upper bound
monte carlo
noisy data
stochastic model