Joost Broekens

TL;DR: In this article, the authors systematically reviewed and analyzed existing literature on the effects of assistive social robots in health care for the elderly, focusing in particular on the companion function, and concluded that more work on methods is needed as well as robust, large-scale studies to establish the positive effects of these devices with respect to the elderly.

TL;DR: No support is found for the emotional sensitivity account, as both genders rated the target emotions as similarly intense at both levels of stimulus intensity, and men, however, more strongly perceived non-target emotions to be present than women.

TL;DR: The results show the reliability, validity, and usability of the button for acquiring three types of affective feedback in various domains and of its relevance to areas including recommender systems, preference elicitation, social computing, online surveys, coaching and tutoring, experimental psychology and psychometrics, content annotation, and game consoles.

TL;DR: A survey of computational models of emotion in reinforcement learning (RL) agents is presented in this article, where the authors focus on agent/robot emotions and mostly ignore human user emotions, and compare evaluation criteria and draw connections to important RL sub-domains like (intrinsic) motivation and model-based RL.

TL;DR: A survey of the integration of model-based reinforcement learning and planning, better known as model- based reinforcement learning, and a broad conceptual overview of planning-learning combinations for MDP optimization are presented.