Efficiency of Empirical Estimators for Markov Chains

By Priscilla E. Greenwood, Wolfgang Wefelmeyer. 1995

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jaimyoung Kwon
2. Peter J. Bickel
3. Tommaso Cai
4. James M. Robins
5. Victor Chernozhukov
6. Alexandre Belloni
7. Jianqing Fan
8. Clifford Lam

Citations in the corpus

• Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning (2019, neutral): “There exist different approaches to this (Bickel and Kwon, 2001; Greenwood and Wefelmeyer, 1995).”
• INFERENCE FOR SEMIPARAMETRIC MODELS: SOME QUESTIONS AND AN ANSWER (2001, background): “The basic result of Greenwood and Wefelmeyer (1995) now follows: b∗(P̂ (2)n ) is an efficient estimate of b∗(P (2)) for b∗ ∈ B∗0.”
• Efficiently Breaking the Curse of Horizon: Double Reinforcement Learning in Infinite-Horizon Processes (2019, unknown): “There exist different approaches to this (Bickel and Kwon, 2001; Greenwood and Wefelmeyer, 1995).”