Login / Signup

A Robust Algorithm to Unifying Offline Causal Inference and Online Multi-armed Bandit Learning.

Qiao TangHong Xie
Published in: ICDM (2021)
Keyphrases
  • learning algorithm
  • online learning
  • causal inference
  • learning process
  • multi armed bandit
  • objective function
  • probabilistic model
  • reinforcement learning
  • optimal solution
  • worst case
  • maximum entropy