Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning

@article{Li2019EfficientRO,
  title={Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning},
  author={Minne Li and Zhiwei Qin and Yan Jiao and Yaodong Yang and Zhichen Gong and Jun Wang and Chenxi Wang and Guobin Wu and Jieping Ye},
  journal={The World Wide Web Conference},
  year={2019}
}
A fundamental question in any peer-to-peer ridesharing system is how to, both effectively and efficiently, dispatch user's ride requests to the right driver in real time. Traditional rule-based solutions usually work on a simplified problem setting, which requires a sophisticated hand-crafted weight design for either centralized authority control or decentralized multi-agent scheduling systems. Although recent approaches have used reinforcement learning to provide centralized combinatorial… Expand
Multi-Agent Reinforcement Learning for Order-dispatching via Order-Vehicle Distribution Matching
TLDR
Experiments show that the proposed decentralized execution order-dispatching method outperforms the baselines in terms of accumulated driver income (ADI) and Order Response Rate (ORR) in various traffic environments. Expand
CoRide: Joint Order Dispatching and Fleet Management for Multi-Scale Ride-Hailing Platforms
TLDR
It is demonstrated that CoRide provides superior performance in terms of platform revenue and user experience in the task of city-wide hybrid order dispatching and fleet management over strong baselines. Expand
Spatial-temporal pricing for ride-sourcing platform with reinforcement learning
TLDR
A reinforcement learning enhanced agent-based modeling and simulation (RL-ABMS) system is proposed to reveal the complex mechanism in the ride-sourcing system and tackle the problem of spatial–temporal pricing for a ride-Sourcing platform. Expand
Equilibrium Inverse Reinforcement Learning for Ride-hailing Vehicle Network
TLDR
This work formulate the problem of passenger-vehicle matching in a sparsely connected graph and proposed an algorithm to derive an equilibrium policy in a multi-agent environment and developed a method to learn the driver’s reward function transferable to an environment with significantly different dynamics from training data. Expand
Deep Reinforcement Learning for Multi-driver Vehicle Dispatching and Repositioning Problem
TLDR
A deep reinforcement learning approach for tackling the full fleet management and dispatching problems and considers the problem from a system-centric perspective, where a central fleet management agent is responsible for decision-making for all drivers. Expand
Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach
  • Haotian Gu, Xin Guo, Xiaoli Wei, Renyuan Xu
  • Computer Science, Mathematics
  • SSRN Electronic Journal
  • 2021
TLDR
This paper proposes a framework called localized training and decentralized execution to study MARL with network of states, with homogeneous agents, and adopts the actor-critic approach with over-parameterized neural networks, and establishes the convergence and sample complexity for the algorithm. Expand
Multi-Agent Reinforcement Learning for Dynamic Routing Games: A Unified Paradigm
TLDR
A multi-agent reinforcement learning (MARL) paradigm is proposed in which each agent learns and updates her own en-route path choice policy while interacting with others on transportation networks and is shown to generalize the classical notion of dynamic user equilibrium (DUE) to model-free and data-driven scenarios. Expand
Multi-Objective Predictive Taxi Dispatch via Network Flow Optimization
TLDR
The results of the simulation studies using the real-world data for the metropolitan area of Seoul, South Korea indicate that the performance of the proposed predictive method is almost as good as that of the oracle that foresees the future. Expand
Optimizing Online Matching for Ride-Sourcing Services with Multi-Agent Deep Reinforcement Learning
TLDR
A two-stage framework which incorporates a combinatorial optimization and multi-agent deep reinforcement learning methods is established and is able to remarkably improve system performances. Expand
Optimizing matching time intervals for ride-hailing services using reinforcement learning
  • Guoyang Qin, Qi Luo, Yafeng Yin, Jian Sun, Jieping Ye
  • Computer Science
  • Transportation Research Part C: Emerging Technologies
  • 2021
TLDR
The focus of this work is single-ride service due to limited access to shared ride data, while the general framework can be extended to the setting with a ride-pooling component and provides a solution to spatial partitioning balance between the state representation error and the optimality gap of asynchronous matching. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 75 REFERENCES
Large-Scale Order Dispatch in On-Demand Ride-Hailing Platforms: A Learning and Planning Approach
TLDR
A novel order dispatch algorithm in large-scale on-demand ride-hailing platforms that is designed to provide a more efficient way to optimize resource utilization and user experience in a global and more farsighted view is presented. Expand
Deep Reinforcement Learning with Knowledge Transfer for Online Rides Order Dispatching
TLDR
This work model the ride dispatching problem as a Markov Decision Process and proposes learning solutions based on deep Q-networks with action search to optimize the dispatching policy for drivers on ride-sharing platforms. Expand
Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning
TLDR
This paper proposes a contextual multi-agent reinforcement learning framework including two concrete algorithms, namely contextual deep Q-learning and contextualmulti-agent actor-critic, to achieve explicit coordination among a large number of agents adaptive to different contexts. Expand
A Collaborative Multiagent Taxi-Dispatch System
TLDR
A novel multiagent approach to automating taxi dispatch that services current bookings in a distributed fashion is presented, populated with software collaborative agents that can actively negotiate on behalf of taxi drivers in groups of size N for available customer bookings. Expand
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
TLDR
Two methods using a multi-agent variant of importance sampling to naturally decay obsolete data and conditioning each agent's value function on a fingerprint that disambiguates the age of the data sampled from the replay memory enable the successful combination of experience replay with multi- agent RL. Expand
Counterfactual Multi-Agent Policy Gradients
TLDR
A new multi-agent actor-critic method called counterfactual multi- agent (COMA) policy gradients, which uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies. Expand
A Taxi Order Dispatch Model based On Combinatorial Optimization
TLDR
A novel system that attempts to optimally dispatch taxis to serve multiple bookings and a method to predict destinations of a user once the taxi-booking APP is started, both deployed in online systems and leading to enhanced user experience. Expand
Multiagent self-organization for a taxi dispatch system
TLDR
This dissertation applies a multiagent self-organization technique to the taxi dispatch problem, dynamically modifying the adjacency of dispatch areas, and discovers that human intervention to manually overcome the limitations of the existing dispatch system can be counterproductive when used with aSelf-organizing system. Expand
Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems
TLDR
This paper identifies several challenges responsible for the non-coordination of independent agents: Pareto-selection, non-stationarity, stochasticity, alter-exploration and shadowed equilibria, and can serve as a basis for choosing the appropriate algorithm for a new domain. Expand
Mean Field Multi-Agent Reinforcement Learning
Existing multi-agent reinforcement learning methods are limited typically to a small number of agents. When the agent number increases largely, the learning becomes intractable due to the curse ofExpand
...
1
2
3
4
5
...