Login / Signup

On the robustness of a one-period look-ahead policy in multi-armed bandit problems.

Ilya O. RyzhovPeter I. FrazierWarren B. Powell
Published in: ICCS (2010)
Keyphrases
  • multi armed bandit problems
  • bandit problems
  • stochastic demand
  • computational efficiency
  • asymptotically optimal
  • machine learning
  • case based reasoning
  • optimal policy