Stochastic Bandits with Delayed Composite Anonymous Feedback.

Siddhant Garg Aditya Kumar Akash

Published in: CoRR (2019)

Keyphrases

stochastic systems
feedback mechanisms
multi armed bandits
neural network
regret bounds
multi armed bandit
real time
information retrieval
learning algorithm
website
digital libraries
artificial neural networks
relevance feedback
stochastic optimization
stochastic models
visual feedback