Login / Signup
Online Learning with Expert Advice and Finite-Horizon Constraints.
Branislav Kveton
Jia Yuan Yu
Georgios Theocharous
Shie Mannor
Published in:
AAAI (2008)
Keyphrases
</>
online learning
finite horizon
expert advice
infinite horizon
optimal policy
optimal stopping
markov decision processes
regret bounds
inventory models
inventory control
yield management
single product
e learning
markov decision process
multistage
non stationary
learning process
expected reward
support vector