A Batch, Off-Policy, Actor-Critic Algorithm for Optimizing the Average Reward

By Susan A. Murphy, Yanzhen Deng, Eric B. Laber, Hamid Reza Maei, Richard S. Sutton, Katie Witkiewitz. 2016

22 citations recorded by the source corpus.

We develop an off-policy actor-critic algorithm for learning an optimal policy from a training set composed of data from multiple individuals. This algorithm is developed with a view towards its use in mobile health.

Subfields: Electrical and Electronic Engineering, Endocrinology, Diabetes and Metabolism, Management Science and Operations Research

How researchers see this paper

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

In Electrical and Electronic Engineering

In Endocrinology, Diabetes and Metabolism

In Management Science and Operations Research

Citations in the corpus

Reinforcement Learning in Healthcare: A Survey (2019, methodology): “It has been also been used for mobile health intervention for college students who drink heavily and smoke cigarettes [184].”
Robust Actor-Critic Contextual Bandit for Mobile Health (mHealth) Interventions (2018, methodology): “. Interventions can be sent via smartphones, or via other wearable devices like a wristband (Dempsey et al. 2016). The Heartsteps is a common application for the contextual bandit algorithm (Lei 2016;Murphy et al. 2016). The goal is to learn an optimal SDM algorithms to decide what type of intervent”
Estimating Dynamic Treatment Regimes in Mobile Health Using V-learning (2016, background): “Ertefaie (2014) introduced GGQ for estimating dynamic treatment regimes in infinite horizon settings (see also Maei et al. 2010; Murphy et al. 2016).”
Group-driven Reinforcement Learning for Personalized mHealth Intervention (2017, methodology): “It aims to learn the optimal decision rule to decide when, where and how to deliver interventions [10,13,14,24,23] to best serve users.”