This article surveys reinforcement learning (RL) approaches in social robotics. RL is a framework for decision-making problems in which an agent interacts through trial-and-error with its environment to discover an optimal behavior. Since interaction is a key component in both RL and social robotics, it can be a well-suited approach for real-world interactions with physically embodied social robots. The scope of the paper is focused particularly on studies that include social physical robots and real-world human-robot interactions with users. In addition to a survey, we categorize existent RL approaches based on the design of the reward mechanisms. This categorization includes three major themes: interactive reinforcement learning, intrinsically motivated methods, and task performance-driven methods. Thus, this paper aims to become a starting point for researchers interested to use and apply reinforcement learning methods in this particular research field.
View on arXiv