L Ren, X Fan, J Cui, Z Shen, Y Lv… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
… method that can predict the optimal number of vehicles in advance is urgently needed. In this work, we propose a novel multi-agentreinforcementlearning … constructs the route iteratively …
… This article presents a multi-agent … of ReinforcementLearning. For better introduction and validation of the AMAM framework, this article uses the instantiation of the VehicleRouting …
… parameters used during learning. We have given a fleet of cars in a multi-agent environment. We … graph under traffic conditions, such that all routes are traversed not less than a defined …
S Mak, L Xu, T Pearce, M Ostroumov… - … Research Part C …, 2023 - Elsevier
… methods. … vehiclerouting and deep multi-agentreinforcementlearning. Section 3 provides a formal introduction to coalitional games, coalitional bargaining and reinforcementlearning. …
… method to handle DS-VRP. Our approach depends on multi-agentreinforcementlearning where we place our decision makers in nodes instead of vehicles and we use geometric …
Z Zong, M Zheng, Y Li, D Jin - Proceedings of the AAAI conference on …, 2022 - ojs.aaai.org
… vehicles is highly related to solution exploration and is difficult to model. In this paper, we propose a novel multi-agentreinforcementlearning… Multi-vehiclerouting problems with soft time …
… We propose to integrate energy scheduling and vehiclerouting into one problem, which significantly increases the problem complexity. To address this challenge, we propose a …
Z Shou, X Chen, Y Fu, X Di - Transportation Research Part C: Emerging …, 2022 - Elsevier
… To efficiently solve MRG, we formulate it as multi-agentreinforcementlearning (MARL) and … a multi-driver route choice task, we develop a multi-agent deep Q-learningapproach in this …
A Arishi, K Krishnan - Journal of Management Analytics, 2023 - Taylor & Francis
… routing problems. This paper proposes a new multi-agent deep reinforcementlearning (… Extensive experiments are conducted to evaluate the performance of the proposed approach. …