Optimal Unbiased Estimators for Evaluating Agent Performance

By Martin A. Zinkevich, Michael H. Bowling, Nolan Bard, Morgan Kan, Darse Billings. 2006

41 citations recorded by the source corpus.

How researchers see this paper

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

1. David Silver
2. Sergey Levine
3. Yuxi Li
4. Emma Brunskill
5. Nan Jiang
6. R´emi Munos
7. Lihong Li
8. Ofir Nachum

Citations in the corpus

• Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning (2016, methodology): “One may therefore view the DR estimator (Jiang & Li, 2015) as the extension of the advantage sum estimator (Zinkevich et al., 2006) to the off-policy setting or as the extension of the doubly robust estimator for bandits ( Dud ´ ık et al., 2011) to the sequential setting.”
• The grand challenge of computer Go (2012, methodology): “One support for this claim is the fact that Monte-Carlo tree search, which was originally introduced in Go, has already started to achieve notable successes in other areas within AI [25, 20].”