Login / Signup

Provably Correct SGD-Based Exploration for Generalized Stochastic Bandit Problem.

Jialin DongJiayi WangLin F. Yang
Published in: SmartNets (2024)
Keyphrases
  • provably correct
  • formal methods
  • situation calculus
  • monte carlo
  • machine learning
  • markov chain
  • multi armed bandit
  • information systems
  • knowledge representation
  • random sampling
  • error estimates