Learning heuristics over large graphs via deep reinforcement learning

S Manchanda, A Mittal, A Dhawan, S Medya… - arXiv preprint arXiv …, 2019 - arxiv.org
… At the core of our study lies the observation that although the graph may be large, …
graph through reinforcement learning. The neural model integrates node embedding and Q-learning

Reinforcement learning on graphs: A survey

M Nie, D Chen, D Wang - IEEE Transactions on Emerging …, 2023 - ieeexplore.ieee.org
… on graphstructured environments. We show the times cited and publications over time of Graph
Reinforcement Learning … 1 to prove the fusion of graph mining methods with RL for graph-…

Challenges and opportunities in deep reinforcement learning with graph neural networks: A comprehensive review of algorithms and applications

S Munikoti, D Agarwal, L Das… - … and learning …, 2023 - ieeexplore.ieee.org
… reveal that the proposed method marginally outperforms S2V-DQN and scales to much larger
graph instances up to 100000 nodes. In addition, it is significantly more efficient in terms of …

Large-scale machine learning cluster scheduling via multi-agent graph reinforcement learning

X Zhao, C Wu - IEEE Transactions on Network and Service …, 2021 - ieeexplore.ieee.org
… avoidance, we adopt a multiagent reinforcement learning (MARL) model to schedule DL …
We design a hierarchical Graph Neural Network (GNN) with edge information encoded to …

IG-RL: Inductive graph reinforcement learning for massive-scale traffic signal control

FX Devailly, D Larocque… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
… We introduce Inductive Graph Reinforcement Learning (IG-RL) based on graph-convolutional
networks which adapts to the structure of any road network, to learn detailed …

Graph convolutional reinforcement learning

J Jiang, C Dun, T Huang, Z Lu - arXiv preprint arXiv:1810.09202, 2018 - arxiv.org
… This makes it hard to learn abstract representations of mutual … graph convolutional
reinforcement learning, where graph convolution adapts to the dynamics of the underlying graph of …

A Distributed-GPU Deep Reinforcement Learning System for Solving Large Graph Optimization Problems

W Zheng, D Wang, F Song - ACM Transactions on Parallel Computing, 2023 - dl.acm.org
learning good heuristics to solve graph optimization problems. However, the existing RL
systems either do not support graph RL … of reinforcement learning in solving large-scale graph

Reinforcement learning with feedback graphs

C Dann, Y Mansour, M Mohri… - Advances in Neural …, 2020 - proceedings.neurips.cc
… As a first contribution, we show the benefits of a feedback graph in achieving more favorable
learning guarantees for optimistic model-based algorithms. Algorithms in this family, such …

[HTML][HTML] A Graph Reinforcement Learning Framework for Neural Adaptive Large Neighbourhood Search

SN Johnn, VA Darvariu, J Handl, J Kalcsics - Computers & Operations …, 2024 - Elsevier
… Machine Learning (ML), an increasingly important tool for combinatorial optimisation (Bengio
et al., 2021). Concretely, we opt for Reinforcement Learning (RL), a framework for learning

Solving maximum weighted matching on large graphs with deep reinforcement learning

B Wu, L Li - Information Sciences, 2022 - Elsevier
… and inspired by the reinforcement learning techniques, we … the MWM problem on large-scale
general graphs. First, since … edge-selection on large-scale graphs, we propose an edge-…