Login / Signup

Asymptotically Optimal Thompson Sampling Based Policy for the Uniform Bandits and the Gaussian Bandits.

Jongyeong LeeChao-Kai ChiangMasashi Sugiyama
Published in: CoRR (2023)
Keyphrases
  • asymptotically optimal
  • asymptotic optimality
  • holding cost
  • arrival rate
  • service rates
  • heavy traffic
  • optimal policy
  • call center
  • regret bounds
  • real time
  • nearest neighbor
  • distributed systems
  • state dependent
  • setup cost