DTR Bandit: Learning to Make Response-Adaptive Decisions With Low Regret.

Yichun Hu Nathan Kallus

Published in: CoRR (2020)

Keyphrases

online learning
learning algorithm
reinforcement learning
making decisions
adaptive control
learning systems
prior knowledge
learning process
learning tasks
learning problems
incremental learning
decision making
active learning
decision makers
decision process
adaptive learning
case study