Graph Neural Network Reinforcement Learning for Autonomous
Mobility-on-Demand Systems
- URL: http://arxiv.org/abs/2104.11434v1
- Date: Fri, 23 Apr 2021 06:42:38 GMT
- Title: Graph Neural Network Reinforcement Learning for Autonomous
Mobility-on-Demand Systems
- Authors: Daniele Gammelli, Kaidi Yang, James Harrison, Filipe Rodrigues,
Francisco C. Pereira, Marco Pavone
- Abstract summary: We argue that the AMoD control problem is naturally cast as a node-wise decision-making problem.
We propose a deep reinforcement learning framework to control the rebalancing of AMoD systems through graph neural networks.
We show how the learned policies exhibit promising zero-shot transfer capabilities when faced with critical portability tasks.
- Score: 42.08603087208381
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Autonomous mobility-on-demand (AMoD) systems represent a rapidly developing
mode of transportation wherein travel requests are dynamically handled by a
coordinated fleet of robotic, self-driving vehicles. Given a graph
representation of the transportation network - one where, for example, nodes
represent areas of the city, and edges the connectivity between them - we argue
that the AMoD control problem is naturally cast as a node-wise decision-making
problem. In this paper, we propose a deep reinforcement learning framework to
control the rebalancing of AMoD systems through graph neural networks.
Crucially, we demonstrate that graph neural networks enable reinforcement
learning agents to recover behavior policies that are significantly more
transferable, generalizable, and scalable than policies learned through other
approaches. Empirically, we show how the learned policies exhibit promising
zero-shot transfer capabilities when faced with critical portability tasks such
as inter-city generalization, service area expansion, and adaptation to
potentially complex urban topologies.
Related papers
- AI Flow at the Network Edge [58.31090055138711]
AI Flow is a framework that streamlines the inference process by jointly leveraging the heterogeneous resources available across devices, edge nodes, and cloud servers.
This article serves as a position paper for identifying the motivation, challenges, and principles of AI Flow.
arXiv Detail & Related papers (2024-11-19T12:51:17Z) - Decentralized Learning Strategies for Estimation Error Minimization with Graph Neural Networks [94.2860766709971]
We address the challenge of sampling and remote estimation for autoregressive Markovian processes in a wireless network with statistically-identical agents.
Our goal is to minimize time-average estimation error and/or age of information with decentralized scalable sampling and transmission policies.
arXiv Detail & Related papers (2024-04-04T06:24:11Z) - Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph
Reinforcement Learning [42.175067773481416]
We design a new decentralized control architecture with improved environmental observability to capture the spatial-temporal correlation.
Specifically, we first develop a topology-aware information aggregation strategy to extract correlation-related information from unstructured data gathered in the road network.
A diffusion convolution module is developed, forming a new MARL algorithm, which endows agents with the capabilities of graph learning.
arXiv Detail & Related papers (2023-11-07T06:43:15Z) - A Novel Multi-Agent Deep RL Approach for Traffic Signal Control [13.927155702352131]
We propose a Friend-Deep Q-network (Friend-DQN) approach for multiple traffic signal control in urban networks.
In particular, the cooperation between multiple agents can reduce the state-action space and thus speed up the convergence.
arXiv Detail & Related papers (2023-06-05T08:20:37Z) - Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility [7.533471021886634]
We introduce the concept of partially observable advanced air mobility games to coordinate a fleet of aerial vehicles.
We propose a novel graph attention-decoder (HetGAT Enc-Dec) network neural-based policy.
We show that the learned policy generalizes to various fleet compositions, demand patterns, and observation topologies.
arXiv Detail & Related papers (2023-02-14T20:48:00Z) - GINK: Graph-based Interaction-aware Kinodynamic Planning via
Reinforcement Learning for Autonomous Driving [10.782043595405831]
There are many challenges in applying deep reinforcement learning (D) to autonomous driving in a structured environment such as an urban area.
In this paper, we suggest a new framework that effectively combines graph-based intention representation and reinforcement learning for dynamic planning.
The experiments show the state-of-the-art performance of our approach compared to the existing baselines.
arXiv Detail & Related papers (2022-06-03T10:37:25Z) - Decentralized Control with Graph Neural Networks [147.84766857793247]
We propose a novel framework using graph neural networks (GNNs) to learn decentralized controllers.
GNNs are well-suited for the task since they are naturally distributed architectures and exhibit good scalability and transferability properties.
The problems of flocking and multi-agent path planning are explored to illustrate the potential of GNNs in learning decentralized controllers.
arXiv Detail & Related papers (2020-12-29T18:59:14Z) - Reinforcement Learning for Autonomous Driving with Latent State
Inference and Spatial-Temporal Relationships [46.965260791099986]
We show that explicitly inferring the latent state and encoding spatial-temporal relationships in a reinforcement learning framework can help address this difficulty.
We encode prior knowledge on the latent states of other drivers through a framework that combines the reinforcement learner with a supervised learner.
The proposed framework significantly improves performance in the context of navigating T-intersections compared with state-of-the-art baseline approaches.
arXiv Detail & Related papers (2020-11-09T08:55:12Z) - Multi-Agent Routing Value Iteration Network [88.38796921838203]
We propose a graph neural network based model that is able to perform multi-agent routing based on learned value in a sparsely connected graph.
We show that our model trained with only two agents on graphs with a maximum of 25 nodes can easily generalize to situations with more agents and/or nodes.
arXiv Detail & Related papers (2020-07-09T22:16:45Z) - IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic
Signal Control [4.273991039651846]
Scaling adaptive traffic-signal control involves dealing with state and action spaces.
We introduce Inductive Graph Reinforcement Learning (IG-RL) based on graph-convolutional networks.
Our model can generalize to new road networks, traffic distributions, and traffic regimes.
arXiv Detail & Related papers (2020-03-06T17:17:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.