Login / Signup
Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms.
Tiancheng Jin
Junyan Liu
Haipeng Luo
Published in:
NeurIPS (2023)
Keyphrases
</>
multi armed bandits
multi armed bandit
special case
bandit problems
optimal solution
dynamic programming
decision problems
machine learning
least squares
maximum likelihood
linear combination
optimal strategy