Optimal treatment allocation for efficient policy evaluation in sequential decision making

Li, Ting, Shi, Chengchun, Wang, Jianing, Zhou, Fan and Zhu, Hongtu (2023) Optimal treatment allocation for efficient policy evaluation in sequential decision making. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M. and Levine, S., (eds.) Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Neural Information Processing Systems Foundation.

Text (Optimal Treatment Allocation for Efficient Policy) - Accepted Version Download (1MB)

• Author

Abstract

A/B testing is critical for modern technological companies to evaluate the effectiveness of newly developed products against standard baselines. This paper studies optimal designs that aim to maximize the amount of information obtained from online experiments to estimate treatment effects accurately. We propose three optimal allocation strategies in a dynamic setting where treatments are sequentially assigned over time. These strategies are designed to minimize the variance of the treatment effect estimator when data follow a non-Markov decision process or a (time-varying) Markov decision process. We further develop estimation procedures based on existing off-policy evaluation (OPE) methods and conduct extensive experiments in various environments to demonstrate the effectiveness of the proposed methodologies. In theory, we prove the optimality of the proposed treatment allocation design and establish upper bounds for the mean squared errors of the resulting treatment effect estimators

Item Type:	Book Section
Official URL:	https://proceedings.neurips.cc/paper_files/paper/2...
Additional Information:	© 2024 The Author(s)
Divisions:	Statistics
Subjects:	H Social Sciences > HA Statistics
Date Deposited:	23 Apr 2024 11:03
Last Modified:	17 Sep 2024 10:30
URI:	http://eprints.lse.ac.uk/id/eprint/122754

Actions (login required)

View Item