Reinforcement learning for sequential decision making in population research

Abstract

Reinforcement learning (RL) algorithms have been long recognized as powerful tools for optimal sequential decision making. The framework is concerned with a decision maker, the agent, that learns how to behave in an unknown environment by making decisions and seeing their associated outcome. The goal of the RL agent is to infer, through repeated experience, an optimal decision-making policy, i.e., a sequence of action rules that would lead to the highest, typically long-term, expected utility. Today, a wide range of domains, from economics to education and healthcare, have embraced the use of RL to address specific problems. To illustrate, we used an RL-based algorithm to design a text-messaging system that delivers personalized real-time behavioural recommendations to promote physical activity and manage depression. Motivated by the recent call of the UNECE for government-wide actions to adapt to population ageing, in this work, we argue that the RL framework may provide a set of compelling strategies for supporting population research and informing population policies. After introducing the RL framework, we discuss its potential in three population-study applications: international migration, public health, and fertility.

Optimizing sequential gene expression modulation for cellular reprogramming - Coupled Boolean modeling and Reinforcement Learning based method

“…The proposed method captures the core dynamics of gene expression regulation with the help of a Boolean model of the concerned gene regulatory network, thereby, representing the core biological context. It further couples this model with Reinforcement Learning, a powerful approach for solving sequential decision-making tasks [67]; thus, allowing the proposed method to predict biologically relevant sequential gene expression modulations for targeted cellular reprogramming.…”

Integration of Deep Reinforcement Learning with Collaborative Filtering for Movie Recommendation Systems

“…Reinforcement learning introduces a unique set of components that include states, actions, environments, agents, and rewards, offering a fresh perspective on how recommendations can be optimized. In reinforcement-learning-based recommendation systems, the user's interactions with the recommendation platform are viewed as a sequential decision-making process [28]. The "state" represents the user's current context, while "actions" refer to the recommendation made to the user.…”