ICML 2022spotlight23 citations

Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory

Ruiqi Zhang, Xuezhou Zhang, Chengzhuo Ni, Mengdi Wang

Abstract

Off-Policy Evaluation (OPE) serves as one of the cornerstones in Reinforcement Learning (RL). Fitted Q Evaluation (FQE) with various function approximators, especially deep neural networks, has gained practical success. While statistical analysis has proved FQE to be minimax-optimal with tabular, linear and several nonparametric function families, its practical performance with more general function approximator is less theoretically understood. We focus on FQE with general

BibTeX
@InProceedings{pmlr-v162-zhang22al,
  title = 	 {Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory},
  author =       {Zhang, Ruiqi and Zhang, Xuezhou and Ni, Chengzhuo and Wang, Mengdi},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {26713--26749},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/zhang22al/zhang22al.pdf},
  url = 	 {https://proceedings.mlr.press/v162/zhang22al.html},
  abstract = 	 {Off-Policy Evaluation (OPE) serves as one of the cornerstones in Reinforcement Learning (RL). Fitted Q Evaluation (FQE) with various function approximators, especially deep neural networks, has gained practical success. While statistical analysis has proved FQE to be minimax-optimal with tabular, linear and several nonparametric function families, its practical performance with more general function approximator is less theoretically understood. We focus on FQE with general