Login / Signup

reBandit: Random Effects based Online RL algorithm for Reducing Cannabis Use.

Susobhan GhoshYongyi GuoPei-Yao HungLara N. CoughlinErin BonarInbal Nahum-ShaniMaureen A. WaltonSusan A. Murphy
Published in: CoRR (2024)
Keyphrases
  • dynamic programming
  • optimal solution
  • learning algorithm
  • expectation maximization
  • artificial neural networks
  • function approximation
  • model free