ICML 2020poster52 citations

Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making

Chengchun Shi, Runzhe Wan, Rui Song, Wenbin Lu, Ling Leng

Abstract

The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning. In this paper, we propose a novel Forward-Backward Learning procedure to test MA in sequential decision making. The proposed test does not assume any parametric form on the joint distribution of the observed data and plays an important role for identifying the optimal policy in high-order Markov decision processes (MDPs) and partially observable MDPs. Theoretically, we establish the validity of our test. Empirically, we apply our test to both synthetic datasets and a real data example from mobile health studies to illustrate its usefulness.

BibTeX
@InProceedings{pmlr-v119-shi20c,
  title = 	 {Does the {M}arkov Decision Process Fit the Data: Testing for the {M}arkov Property in Sequential Decision Making},
  author =       {Shi, Chengchun and Wan, Runzhe and Song, Rui and Lu, Wenbin and Leng, Ling},
  booktitle = 	 {Proceedings of the 37th International Conference on Machine Learning},
  pages = 	 {8807--8817},
  year = 	 {2020},
  editor = 	 {III, Hal Daumé and Singh, Aarti},
  volume = 	 {119},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {13--18 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v119/shi20c/shi20c.pdf},
  url = 	 {https://proceedings.mlr.press/v119/shi20c.html},
  abstract = 	 {The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning. In this paper, we propose a novel Forward-Backward Learning procedure to test MA in sequential decision making. The proposed test does not assume any parametric form on the joint distribution of the observed data and plays an important role for identifying the optimal policy in high-order Markov decision processes (MDPs) and partially observable MDPs. Theoretically, we establish the validity of our test. Empirically, we apply our test to both synthetic datasets and a real data example from mobile health studies to illustrate its usefulness.}
}
Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making · ICML 2020