Login / Signup

Sub-sampling for Multi-armed Bandits.

Akram BaransiOdalric-Ambrym MaillardShie Mannor
Published in: ECML/PKDD (1) (2014)
Keyphrases
  • multi armed bandits
  • multi armed bandit
  • bandit problems
  • reinforcement learning
  • random sampling
  • sample size
  • monte carlo
  • lower bound
  • upper bound
  • information theoretic