Qingyuan Zhao
Qingyuan Zhao
Posts
Talks
Publications
Teaching
Students
Links
Light
Dark
Automatic
Sequential Decisions
A graphical approach to state variable selection in off-policy learning
We give graphical criteria for state variables to be 'valid' in off-policy learning in a framework that generalizes dynamic treatment regimes (DTRs) and Markov decision processes (MDPs).
Cite
×