Diversity-Oriented Route Planning for Tourists

Touring route planning is an essential part of e-tourism, and significantly aids the development of the tourism industry. Several models have been proposed to formalize the touring route-planning problem with promising results. Most existing models consider only one tourist and return the same or similar results to tourists if they issue the same or similar queries when multiple users use the system simultaneously, which may cause congestion problems. In this study, we introduce a novel diversity-oriented touring route planning problem, and propose a multi-agent reinforcement learning approach with a dynamic reward mechanism. Experimental results show that our method significantly improves the diversity of the planned routes, reducing the bias of visiting locations and improving the total gain of all tourists.