mlsanityData to 14 Oct 2026

Relational inductive bias for physical construction in humans and machines

arXiv 1806.01203 ↗First posted 4 Jun 2018cs.LG cs.AI stat.MLcited by 44

Not on the map. Why?

Abstract (arXiv)

While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of blocks. We hypothesize that what these systems lack is a "relational inductive bias": a capacity for reasoning about inter-object relations and making choices over a structured description of a scene. To test this hypothesis, we focus on a task that involves gluing pairs of blocks together to stabilize a tower, and quantify how well humans perform. We then introduce a deep reinforcement learning agent which uses object- and relation-centric scene and policy representations and apply it to the task. Our results show that these structured representations allow the agent to outperform both humans and more naive approaches, suggesting that relational inductive bias is an important component in solving structured reasoning problems and for building more intelligent, flexible machines.

Key facts. Cited by 44 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 5; 2023: 8; 2024: 12; 2025: 4; 2026: 4.

44 papers.

Sort:

By area:

  1. 2021Combinatorial optimization and reasoning with graph neural networkscited by 268
  2. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  3. 2022The CLRS Algorithmic Reasoning Benchmarkcited by 106
  4. 2021Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapescited by 71
  5. 2021Learning Visible Connectivity Dynamics for Cloth Smoothingcited by 62
  6. 2022A Generalist Neural Algorithmic Learnercited by 59
  7. 2024CANOS: A Fast and Scalable Neural AC-OPF Solver Robust To N-1 Perturbationscited by 27
  8. 2023Dual Algorithmic Reasoningcited by 21
  9. 2021Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learningcited by 19
  10. 2023Neural Algorithmic Reasoning for Combinatorial Optimisationcited by 19
  11. 2021Large-scale graph representation learning with very deep GNNs and self-supervisioncited by 18
  12. 2023Neural Relational Inference with Fast Modular Meta-learningcited by 16
32 more
  1. 2024Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspectivecited by 16
  2. 2021Persistent Message Passingcited by 13
  3. 2021Reasoning-Modulated Representationscited by 13
  4. 2023Asynchronous Algorithmic Alignment with Cocyclescited by 13
  5. 2021Algorithmic Concept-based Explainable Reasoningcited by 12
  6. 2021Active Learning of Abstract Plan Feasibilitycited by 11
  7. 2023Constraining Generative Models for Engineering Design with Negative Datacited by 11
  8. 2024On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methodscited by 11
  9. 2024Discrete Neural Algorithmic Reasoningcited by 9
  10. 2025Primal-Dual Neural Algorithmic Reasoningcited by 9
  11. 2023Neural Priority Queues for Graph Neural Networkscited by 7
  12. 2025Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agentscited by 7
  13. 2024Deep Equilibrium Algorithmic Reasoningcited by 6
  14. 2023Feudal Graph Reinforcement Learningcited by 4
  15. 2024Reconstructing short-lived particles using hypergraph representation learningcited by 4
  16. 2022Compositional Law Parsing with Latent Random Functionscited by 3
  17. 2024Open-Book Neural Algorithmic Reasoningcited by 3
  18. 2024NAR-*ICP: Neural Execution of Classical ICP-based Pointcloud Registration Algorithmscited by 2
  19. 2024Neural Symbolic Regression of Complex Network Dynamicscited by 2
  20. 2022Learning heuristics for A*cited by 1
  21. 2022Solving Reasoning Tasks with a Slot Transformercited by 1
  22. 2023Self Attention with Temporal Prior: Can We Learn More from Arrow of Time?cited by 1
  23. 2024The Deep Equilibrium Algorithmic Reasonercited by 1
  24. 2021Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modellingcited by 0
  25. 2024LightningNet: Distributed Graph-based Cellular Network Performance Forecasting for the Edgecited by 0
  26. 2024Algorithm-Informed Graph Neural Networks for Leakage Detection and Localization in Water Distribution Networkscited by 0
  27. 2025Graph Neural Network-Based Predictive Modeling for Robotic Plaster Printingcited by 0
  28. 2025Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learningcited by 0
  29. 2026Predictive Representations for Skill Transfer in Reinforcement Learningcited by 0
  30. 2026Enabling Structure-Only Initialization and Out-of-Distribution Generalization in GNN-based Molecular Dynamics Simulatorscited by 0
  31. 2026Relational Structural Causal Modelscited by 0
  32. 2026Neural Algorithmic Reasoning for Graph Saddle Point Problemscited by 0