Factored DRO: Factored Distributionally Robust Policies for Contextual Bandits.

Tong Mu Yash Chandak Tatsunori B. Hashimoto Emma Brunskill

Published in: NeurIPS (2022)

Keyphrases

state space
optimal policy
robust optimization
revenue management
factored markov decision processes
neural network
computationally efficient
context dependent
robust estimation
dynamic bayesian networks
management policies