Statistically efficient advantage learning for offline reinforcement learning in infinite horizons
Journal of the American Statistical Association, 2024•Taylor & Francis
We consider reinforcement learning (RL) methods in offline domains without additional
online data collection, such as mobile health applications. Most of existing policy
optimization algorithms in the computer science literature are developed in online settings
where data are easy to collect or simulate. Their generalizations to mobile health
applications with a pre-collected offline dataset remain are less explored. The aim of this
article is to develop a novel advantage learning framework in order to efficiently use pre …
online data collection, such as mobile health applications. Most of existing policy
optimization algorithms in the computer science literature are developed in online settings
where data are easy to collect or simulate. Their generalizations to mobile health
applications with a pre-collected offline dataset remain are less explored. The aim of this
article is to develop a novel advantage learning framework in order to efficiently use pre …
Abstract
We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications. Most of existing policy optimization algorithms in the computer science literature are developed in online settings where data are easy to collect or simulate. Their generalizations to mobile health applications with a pre-collected offline dataset remain are less explored. The aim of this article is to develop a novel advantage learning framework in order to efficiently use pre-collected data for policy optimization. The proposed method takes an optimal Q-estimator computed by any existing state-of-the-art RL algorithms as input, and outputs a new policy whose value is guaranteed to converge at a faster rate than the policy derived based on the initial Q-estimator. Extensive numerical experiments are conducted to back up our theoretical findings. A implementation of our proposed method is available at https://github.com/leyuanheart/SEAL. Supplementary materials for this article are available online.
![](https://scholar.google.com/scholar/images/qa_favicons/tandfonline.com.png)