Recommender systems (RSs) have become an inseparable part of our everyday lives. They help us find our favorite items to purchase, our friends on social networks, and our favorite movies to watch. Traditionally, the recommendation problem was considered to be a classification or prediction problem, but it is now widely agreed that formulating it as a sequential decision problem can better reflect the user-system interaction. Therefore, it can be formulated as a Markov decision process (MDP) and be solved by reinforcement learning (RL) algorithms. Unlike traditional recommendation methods, including collaborative filtering and content-based filtering, RL is able to handle the sequential, dynamic user-system interaction and to take into account the long-term user engagement. Although the idea of using RL for recommendation is not new and has been around for about two decades, it was not very practical, mainly because of scalability problems of traditional RL algorithms. However, a new trend has emerged in the field since the introduction of deep reinforcement learning (DRL) , which made it possible to apply RL to the recommendation problem with large state and action spaces. In this paper, a survey on reinforcement learning based recommender systems (RLRSs) is presented. Our aim is to present an outlook on the field and to provide the reader with a fairly complete knowledge of key concepts of the field. We first recognize and illustrate that RLRSs can be generally classified into RL- and DRL-based methods. Then, we propose an RLRS framework with four components, i.e., state representation, policy optimization, reward formulation, and environment building, and survey RLRS algorithms accordingly. We highlight emerging topics and depict important trends using various graphs and tables. Finally, we discuss important aspects and challenges that can be addressed in the future.

Providing a patient with decision support involves helping that person to choose among two or more elective health care options. “Values Clarification” and “Preference Elicitation” are integral to the full decision-support process. During values clarification, the patient and clinician gain insight into the importance that the patient ascribes to the options’ positive and negative characteristics. During preference elicitation, the patient identifies which options are, overall, personally most favored (and, by corollary, which are least favored). This article identifies the roles that values clarification/preference elicitation (VC/PE) play in the full process of patients’ decision support, outlines various approaches to fostering VC/PE, and poses some fundamental and applied research questions about VC/PE. It also argues that, in order to proceed to answer the posed research questions, investigators in the field of patients’ decision support require a systematic set of criteria for comparing the performance of different VC/PE techniques.