mlsanityData to 14 Oct 2026

Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement

arXiv 2509.09219 ↗First posted 11 Sep 2025cs.LG cs.AIcited by 2

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

We present and evaluate Vejde; a framework which combines data abstraction, graph neural networks and reinforcement learning to produce inductive policy functions for decision problems with richly structured states, such as object classes and relations. MDP states are represented as data bases of facts about entities, and Vejde converts each state to a bipartite graph, which is mapped to latent states through neural message passing. The factored representation of both states and actions allows Vejde agents to handle problems of varying size and structure. We tested Vejde agents on eight problem domains defined in RDDL, with ten problem instances each, where policies were trained using both supervised and reinforcement learning. To test policy generalization, we separate problem instances in two sets, one for training and the other solely for testing. Test results on unseen instances for the Vejde agents were compared to MLP agents trained on each problem instance, as well as the online planning algorithm Prost. Our results show that Vejde policies in average generalize to the test instances without a significant loss in score. Additionally, the inductive agents received scores on unseen test instances that on average were close to the instance-specific MLP agents.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 26 of its 55 references that are in the map. First posted on arXiv 11 Sep 2025.

Builds on

26 of 55 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  4. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  6. 2017Deep Setscited by 1,421
  7. 2015Gated Graph Sequence Neural Networkscited by 796
  8. 2017Counterfactual Multi-Agent Policy Gradientscited by 751
  9. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  10. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  11. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  12. 2023Rethinking the Expressive Power of GNNs via Graph Biconnectivitycited by 119
14 more
  1. 2021The Logic of Graph Neural Networkscited by 85
  2. 2020Neural Enhanced Belief Propagation on Factor Graphscited by 57
  3. 2018Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learningcited by 53
  4. 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 46
  5. 2020Belief Propagation Neural Networkscited by 33
  6. 2022Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policiescited by 23
  7. 2024Return to Tradition: Learning Reliable Heuristics with Classical Machine Learningcited by 19
  8. 2023Structure in Deep Reinforcement Learning: A Survey and Open Problemscited by 16
  9. 2023Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approachcited by 15
  10. 2019Size Independent Neural Transfer for RDDL Planningcited by 12
  11. 2024Entity-based Reinforcement Learning for Autonomous Cyber Defencecited by 11
  12. 2024Structural Generalization in Autonomous Cyber Incident Response with Message-Passing Neural Networks and Reinforcement Learningcited by 7
  13. 2024Learning More Expressive General Policies for Classical Planning Domainscited by 5
  14. 2024Graph Learning for Numeric Planningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A Cyber Range Evaluation of Autonomous Network Incident Response Agentscited by 0
  2. 2026The MAL Simulator: Cyber Operations Simulation based on Attack & Defense Graphscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Dynamic Deep Factor Graph for Multi-Agent Reinforcement Learning
  2. 2025Graph Neural Networks, Deep Reinforcement Learning and Probabilistic Topic Modeling for Strategic Multiagent Settings
  3. 2025Graph-Enhanced Policy Optimization in LLM Agent Training
  4. 2022Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning
  5. 2025Policy-Conditioned Policies for Multi-Agent Task Solving
  6. 2025A Survey of State Representation Learning for Deep Reinforcement Learning
  7. 2026GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents
  8. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks