… a robust and scalable approach that integrates reinforcement learning (RL) and a centralized
… the taxi dispatching problem studied in this article, two lines of research, order dispatching, …

… taxi dispatching approach that incorporates rich contexts into DRL modeling for more efficient
taxi … -aware approach to improve the deep reinforcement learning based taxi dispatching. …

… reinforcement learning framework to solve the taxi dispatch problem. The framework can be
used to redistribute vehicles when the travel demand and taxi … deep reinforcement learning …

… reinforcement learning to combinatorial optimization, we adopt an online learning manner to
adapt the learned dispatching … To avoid the cold start problem in reinforcement learning, we …

… taxi dispatching … reinforcement learning method for order-dispatching via matching the
distribution of orders and vehicles. Results on the three cases in the simulated orderdispatching …

… driverless taxis in advance. In this paper, we consider the driverless taxi dispatch problem (…
system to control a fleet of driverless taxis that provide taxi services, and rebalance the fleet in …

… destinations are indexed in a hexagonal grid world, which is widely adopted by online
taxi platforms like Didi Chuxing and Uber. In this case, all the coordinates are converted to …

… Through an extensive set of experiments, we demonstrate the learning and optimization
capabilities of our deep reinforcement learning algorithms. We further show that dispatching …

… horizon, we incorporated reinforcement learning into our solution framework by developing
tailored algorithms to compute the long-term value of a given dispatching policy, which would…

… Taxi dispatch system based on current demands and real-time traffic conditions. Transportation
Research Record: Journal of the Transportation Research Board 1882 (2004), 193– …