Counterfactual Contextual Multi-Armed Bandit: a Real-World Application to Diagnose Apple Diseases.

Gabriele Sottocornola Fabio Stella Markus Zanker

Published in: CoRR (2021)

Keyphrases

multi armed bandit
multi armed bandits
reinforcement learning
early diagnosis
model based diagnosis
regret bounds
active learning
noise model
decentralized decision making