mlsanityData to 14 Oct 2026

Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control

arXiv 2509.14431 ↗First posted 17 Sep 2025cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

Multi-agent reinforcement learning (MARL) policies for swarm control often learn inefficiently and generalize poorly across coordinate frames, team sizes, and agent roles. We introduce Local-Canonicalization Equivariant Graph Neural Networks (LEGO), a modular policy architecture that combines agent-centric canonicalization with role-aware graph encoding. Canonicalization removes dependence on the global coordinate frame, while transforming predicted local actions back to the world frame produces an E(2)-equivariant policy. Role-wise graph encoders provide intra-role permutation equivariance and fixed-dimensional representations for variable-size teams. LEGO can be paired with standard MARL algorithms; we instantiate it with MAPPO. Across cooperative MPE Spread and competitive Tag-occlusion benchmarks, LEGO-MAPPO improves sample efficiency and task performance relative to MLP-based, graph-only, canonicalization-only, and equivariant baselines. The learned policies transfer without fine-tuning to unseen team sizes, maintain performance under spatial distribution shifts, and benefit from curriculum initialization for larger teams. In Crazyflie experiments, the policy remains operational after one pursuer is disabled. Code is available at https://github.com/CAB-Lab-Princeton/LEGO-MARL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 47 of its 67 references that are in the map. First posted on arXiv 17 Sep 2025.

Builds on

47 of 67 references.

References · 47

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  5. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  6. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  7. 2016Group Equivariant Convolutional Networkscited by 1,165
  8. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  9. 2021E(n) Equivariant Graph Neural Networkscited by 965
  10. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  11. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  12. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
35 more
  1. 2018Spherical CNNscited by 456
  2. 2016Steerable CNNscited by 305
  3. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  4. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 248
  5. 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 228
  6. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 220
  7. 2017Teacher-Student Curriculum Learningcited by 210
  8. 2018Graph Convolutional Reinforcement Learningcited by 152
  9. 2017Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observabilitycited by 148
  10. 2020MDP Homomorphic Networks: Group Symmetries in Reinforcement Learningcited by 142
  11. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 137
  12. 2022SO(2)-Equivariant Reinforcement Learningcited by 84
  13. 2023Attending to Graph Transformerscited by 83
  14. 2021SE(3) Equivariant Graph Neural Networks with Complete Local Framescited by 76
  15. 2021Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificatescited by 74
  16. 2023Heterogeneous-Agent Reinforcement Learningcited by 69
  17. 2022Benchmarking Graphormer on Large-Scale Molecular Modeling Datasetscited by 64
  18. 2019PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learningcited by 47
  19. 2019Equivariant Multi-View Networkscited by 45
  20. 2019Learning Transferable Cooperative Behavior in Multi-Agent Teamscited by 44
  21. 2023Multi-agent Reinforcement Learning: A Comprehensive Surveycited by 33
  22. 2021Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Compositioncited by 30
  23. 2024A Canonicalization Perspective on Invariant and Equivariant Learningcited by 27
  24. 2024Equivariant Reinforcement Learning under Partial Observabilitycited by 18
  25. 2024Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message Passingcited by 15
  26. 2022A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learningcited by 14
  27. 2024Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariancecited by 10
  28. 2024Leveraging Graph Neural Networks and Multi-Agent Reinforcement Learning for Inventory Control in Supply Chainscited by 10
  29. 2025SE(3)-Equivariant Robot Learning and Control: A Tutorial Surveycited by 10
  30. 2025GAGrasp: Geometric Algebra Diffusion for Dexterous Graspingcited by 8
  31. 2023rm E(3)-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learningcited by 6
  32. 2024Graph Neural Network-based Multi-agent Reinforcement Learning for Resilient Distributed Coordination of Multi-Robot Systemscited by 5
  33. 2024Learning Color Equivariant Representationscited by 5
  34. 2024Behavior-Inspired Neural Networks for Relational Inferencecited by 5
  35. 2025PEnGUiN: Partially Equivariant Graph NeUral Networks for Sample Efficient MARLcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Symmetries-enhanced Multi-Agent Reinforcement Learning
  2. 2025Emergent Heterogeneous Swarm Control Through Hebbian Learning
  3. 2026Modular Reinforcement Learning For Cooperative Swarms
  4. 2024A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocation
  5. 2025Collective Behavior Clone with Visual Attention via Neural Interaction Graph Prediction
  6. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
  7. 2025Centralized Permutation Equivariant Policy for Cooperative Multi-Agent Reinforcement Learning
  8. 2025Deep Reinforcement Learning for Multi-Agent Coordination