mlsanityData to 7 Oct 2026

Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications

arXiv 2206.07922 ↗First posted 16 Jun 2022cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning (DRL) has empowered a variety of artificial intelligence fields, including pattern recognition, robotics, recommendation-systems, and gaming. Similarly, graph neural networks (GNN) have also demonstrated their superior performance in supervised learning for graph-structured data. In recent times, the fusion of GNN with DRL for graph-structured environments has attracted a lot of attention. This paper provides a comprehensive review of these hybrid works. These works can be classified into two categories: (1) algorithmic enhancement, where DRL and GNN complement each other for better utility; (2) application-specific enhancement, where DRL and GNN support each other. This fusion effectively addresses various complex problems in engineering and life sciences. Based on the review, we further analyze the applicability and benefits of fusing these two domains, especially in terms of increasing generalizability and reducing computational complexity. Finally, the key challenges in integrating DRL and GNN, and potential future research directions are highlighted, which will be of interest to the broader machine learning community.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 90 of its 181 references that are in the map. First posted on arXiv 16 Jun 2022.

Builds on

90 of 181 references.

References · 90

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  6. 2015Continuous control with deep reinforcement learningcited by 3,279
  7. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  9. 2015Trust Region Policy Optimizationcited by 2,503
  10. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  11. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  12. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
38 more
  1. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  3. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  4. 2015Pointer Networkscited by 882
  5. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
  6. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  7. 2019Heterogeneous Graph Attention Networkcited by 732
  8. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  9. 2019Green AIcited by 620
  10. 2016Neural Combinatorial Optimization with Reinforcement Learningcited by 600
  11. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
  12. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  13. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  14. 2017Deep Reinforcement Learning: An Overviewcited by 327
  15. 2018Reinforcement Learning for Solving the Vehicle Routing Problemcited by 327
  16. 2018Adversarial Attack on Graph Structured Datacited by 300
  17. 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 265
  18. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 259
  19. 2020Reinforcement Learning for Combinatorial Optimization: A Surveycited by 235
  20. 2019Position-aware Graph Neural Networkscited by 203
  21. 2021Identity-aware Graph Neural Networkscited by 197
  22. 2022Online Decision Transformercited by 194
  23. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  24. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 170
  25. 2019A Survey of Reinforcement Learning Informed by Natural Languagecited by 154
  26. 2019Graph Neural Ordinary Differential Equationscited by 153
  27. 2018Graph Convolutional Reinforcement Learningcited by 148
  28. 2017Heterogeneous Information Network Embedding for Recommendationcited by 133
  29. 2016Discriminative Embeddings of Latent Variable Models for Structured Datacited by 130
  30. 2020One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Controlcited by 114
  31. 2018Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learningcited by 101
  32. 2019Deep Coordination Graphscited by 96
  33. 2020Explainability in Deep Reinforcement Learningcited by 96
  34. 2018Convolutional Neural Network Architectures for Signals Supported on Graphscited by 94
  35. 2020GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learningcited by 89
  36. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 81
  37. 2019Auto-GNN: Neural Architecture Search of Graph Neural Networkscited by 73
  38. 2018Relational Deep Reinforcement Learningcited by 72

50 most cited of 90 All 90 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 10; 2025: 9; 2026: 3.

27 papers.

Sort:

By area:

  1. 2024Graph Neural Networks for Financial Fraud Detection: A Reviewcited by 24
  2. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  3. 2023Graph Decision Transformercited by 20
  4. 2023Machine Learning for Large-Scale Optimization in 6G Wireless Networkscited by 18
  5. 2025Graph World Modelcited by 14
  6. 2023Deep Reinforcement Learning for Autonomous Cyber Defence: A Surveycited by 6
  7. 2024Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and Morecited by 6
  8. 2024Graph Reinforcement Learning for Power Grids: A Comprehensive Surveycited by 6
  9. 2025BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatchcited by 6
  10. 2022Proximal Policy Optimization with Graph Neural Networks for Optimal Power Flowcited by 4
  11. 2024Survey of Graph Neural Network for Internet of Things and NextG Networkscited by 4
  12. 2025Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challengescited by 4
15 more
  1. 2023Intrinsically motivated graph exploration using network theories of human curiositycited by 3
  2. 2024Towards a Dynamic Future with Adaptable Computing and Network Convergence (ACNC)cited by 3
  3. 2024Offline reinforcement learning for job-shop scheduling problemscited by 2
  4. 2024Heterogeneous Graph Reinforcement Learning for Dependency-aware Multi-task Allocation in Spatial Crowdsourcingcited by 1
  5. 2025Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex Taskscited by 1
  6. 2024Graph Neural Networks and Reinforcement Learning for Proactive Application Image Placementcited by 0
  7. 2024Balanced Edge Pruning for Graph Anomaly Detection with Noisy Labelscited by 0
  8. 2024Focus Where It Matters: Graph Selective State Focused Attention Networkscited by 0
  9. 2025Enhancing Trust Management System for Connected Autonomous Vehicles Using Machine Learning Methods: A Surveycited by 0
  10. 2025From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Controlcited by 0
  11. 2025Optimizing Drivers' Discount Order Acceptance Strategies: A Policy-Improved Deep Deterministic Policy Gradient Frameworkcited by 0
  12. 2025Exploring a Graph-based Approach to Offline Reinforcement Learning for Sepsis Treatmentcited by 0
  13. 2026HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous Cloudcited by 0
  14. 2026PORL: Pretrained Offline Reinforcement Learning for the Job Shop Scheduling Problemcited by 0
  15. 2026Investigating the Effect of k-NN Preprocessing on Developing Graph Neural Networks: A Fairness-Based Perspectivecited by 0