Dynamic Pricing for Vehicle Dispatching in Mobility-as-a-Service Market via Multi-Agent Deep Reinforcement Learning

Vehicle dispatching in the mobility-as-a-service (MaaS) market has gradually become a situation of multi-service provider competition and coexistence. However, most existing research on vehicle dispatching with dynamic pricing for the MaaS market is still limited to single-service provider scenarios. In this paper, we propose an economic model that analyzes the vehicle dispatching service pricing and demand interactions between multiple mobility service providers (MSPs) and passengers, respectively. We formulate the vehicle dispatching service pricing and demand problem as a two-stage Stackelberg game under different pricing schemes, namely,
independent pricing scheme (IPS)
and
competitive pricing scheme (CPS)
, considering the vehicle supply-demand relationship and market competition among the MSPs. The MSPs, as leaders, set their service pricing strategies first, and then the passengers, as the followers, determine their service demands. Due to the high-dimensional and complicated nature of the dynamic MaaS market environment, we develop a multi-agent deep reinforcement learning (MADRL) algorithm to achieve the Nash equilibrium (NE) of the formulated game, which indicates the optimal pricing and demand strategies for MSPs and passengers. Simulation results and analysis show that the proposed MADRL-based algorithm converges to the optimal solution and outperforms other benchmark schemes under both IPS and CPS in terms of maximizing MSPs' revenue and protecting passengers' benefits. Furthermore, the proposed MADRL-based algorithm under CPS improves MSPs' market attractiveness and long-term benefits, which encourages MSPs to participate in competitive vehicle dispatching in the MaaS market.