Login / Signup
Minimax-Optimal Policy Learning Under Unobserved Confounding.
Nathan Kallus
Angela Zhou
Published in:
Manag. Sci. (2021)
Keyphrases
</>
optimal policy
reinforcement learning
state space
learning algorithm
dynamic programming
markov decision processes
bayesian reinforcement learning
average reward reinforcement learning
multistage
decision problems
state dependent
hidden variables
partially observed