We consider estimation of parameters defined as linear functionals of
so...
In this paper, we study nonparametric estimation of instrumental variabl...
Safety is a crucial necessity in many applications of reinforcement lear...
We study off-policy evaluation (OPE) for partially observable MDPs (POMD...
This paper analyzes the working or default assumptions researchers in th...
In applications of offline reinforcement learning to observational data,...
Topic models are widely used in studying social phenomena. We conduct a
...
The conditional moment problem is a powerful formulation for describing
...
Off-policy evaluation (OPE) in reinforcement learning is an important pr...
Recent work on policy learning from observational data has highlighted t...
Evaluating novel contextual bandit policies using logged data is crucial...
Instrumental variable analysis is a powerful tool for estimating causal
...
We propose to decompose instruction execution to goal prediction and act...
We introduce a method for following high-level navigation instructions b...