Quality of Experience in Cyber-Physical Social Systems Based on Reinforcement Learning and Game Theory

This paper addresses the problem of museum visitors’ Quality of Experience (QoE) optimization by viewing and treating the museum environment as a cyber-physical social system. To achieve this goal, we harness visitors’ internal ability to intelligently sense their environment and make choices that improve their QoE in terms of which the museum touring option is the best for them and how much time to spend on their visit. We model the museum setting as a distributed non-cooperative game where visitors selfishly maximize their own QoE. In this setting, we formulate the problem of Recommendation Selection and Visiting Time Management (RSVTM) and propose a two-stage distributed algorithm based on game theory and reinforcement learning, which learns from visitor behavior to make on-the-fly recommendation selections that maximize visitor QoE. The proposed framework enables autonomic visitor-centric management in a personalized manner and enables visitors themselves to decide on the best visiting strategies. Experimental results evaluating the performance of the proposed RSVTM algorithm under realistic simulation conditions indicate the high operational effectiveness and superior performance when compared to other recommendation approaches. Our results constitute a practical alternative for museums and exhibition spaces meant to enhance visitor QoE in a flexible, efficient, and cost-effective manner.