积分器
数学优化
计算机科学
水准点(测量)
强化学习
部分可观测马尔可夫决策过程
图形
供求关系
运筹学
马尔可夫链
工程类
人工智能
马尔可夫模型
机器学习
数学
经济
理论计算机科学
计算机网络
大地测量学
带宽(计算)
微观经济学
地理
作者
Yinquan Wang,Jianjun Wu,Huijun Sun,Ying Lv,Junyi Zhang
出处
期刊:IEEE Transactions on Intelligent Transportation Systems
[Institute of Electrical and Electronics Engineers]
日期:2024-01-16
卷期号:25 (7): 6889-6901
标识
DOI:10.1109/tits.2023.3348764
摘要
The integrated ride-sourcing mode, developed by third-party integrators, is a feasible solution to market fragmentation because it integrates travel demand and vehicle supply. However, intense competition between platforms reduces the efficiency of the dispatching process. To tackle this issue, a two-stage dispatching framework is proposed, utilizing a partially observable Markov decision process (POMDP) to model the dispatching problem as a mixed cooperative-competitive reinforcement learning task. Within this framework, the Multi-Graph Hierarchical Multi-Head Attention-Deep Deterministic Policy Gradient (MGHMHA-DDPG) algorithm is proposed to determine the generalized values of driver-passenger pairs. A combinatorial optimization model is then formulated to identify the dispatching scheme that maximizes these values. Furthermore, the MGHMHA-DDPG algorithm incorporates a multi-graph convolutional module, a hierarchical multi-head attention module, and a gated recurrent module to model the global supply-demand distribution, the cooperation potential of vehicles, and the hidden features of the temporal dimension, respectively. Experiments using Beijing-based data demonstrate that the MGHMHA-DDPG algorithm outperforms benchmark methods in terms of market revenues and order response rates. This indicates that the MGHMHA-DDPG algorithm effectively mitigates dispatching conflicts between platforms and enhances overall market efficiency.
科研通智能强力驱动
Strongly Powered by AbleSci AI