Login / Signup

A comparison between UCB and UCB-Tuned as selection policies in GGP.

Iván Francisco-ValenciaJosé Raymundo Marcial-RomeroRosa María Valdovinos Rosas
Published in: J. Intell. Fuzzy Syst. (2019)
Keyphrases
  • bandit problems
  • multi armed bandit
  • real time
  • optimal policy
  • information retrieval
  • neural network
  • image sequences
  • expert systems