Login / Signup
Optimal cross-learning for contextual bandits with unknown context distributions.
Jon Schneider
Julian Zimmert
Published in:
NeurIPS (2023)
Keyphrases
</>
active learning
contextual information
learning algorithm
context dependent
reinforcement learning
learning systems
prior knowledge
online learning
multi armed bandits
neural network
learning scheme
learning tasks
worst case
learning process
multi agent
knowledge base
feature selection
machine learning