Harnessing Infinite-Horizon Off-Policy Evaluation: Double Robustness via Duality

By Ziyang Tang. 2019

How researchers see this paper

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

1. Masatoshi Uehara
2. Nathan Kallus
3. Jiawei Huang
4. Nan Jiang
5. Ziyang Tang
6. Sergey Levine
7. Ofir Nachum
8. Ruosong Wang

Citations in the corpus

• Minimax Confidence Interval for Off-Policy Evaluation and Policy Optimization (2020, background): “This is related to but different from the usual notion of double robustness in RL [15, 3, 16, 17]: classical doubly robust methods are typically “meta”-estimators and require a value-function whose estimation procedure is unspecified, and the double robustness refers to the fact that the estimation ”
• Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning (2020, methodology): “Also in the pre-specified evaluation policy and known behavior policy case, Tang et al. (2020) propose an estimator with a form similar to Eq.”