mlsanityData to 14 Oct 2026

SDHN: Skewness-Driven Hypergraph Networks for Enhanced Localized Multi-Robot Coordination

arXiv 2504.06684 ↗First posted 9 Apr 2025cs.RO cs.MAcited by 1

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

Multi-Agent Reinforcement Learning is widely used for multi-robot coordination, where simple graphs typically model pairwise interactions. However, such representations fail to capture higher-order collaborations, limiting effectiveness in complex tasks. While hypergraph-based approaches enhance cooperation, existing methods often generate arbitrary hypergraph structures and lack adaptability to environmental uncertainties. To address these challenges, we propose the Skewness-Driven Hypergraph Network (SDHN), which employs stochastic Bernoulli hyperedges to explicitly model higher-order multi-robot interactions. By introducing a skewness loss, SDHN promotes an efficient structure with Small-Hyperedge Dominant Hypergraph, allowing robots to prioritize localized synchronization while still adhering to the overall information, similar to human coordination. Extensive experiments on Moving Agents in Formation and Robotic Warehouse tasks validate SDHN's effectiveness, demonstrating superior performance over state-of-the-art baselines.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 23 of its 34 references that are in the map. First posted on arXiv 9 Apr 2025.

Builds on

23 of 34 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024MFC-EQ: Mean-Field Control with Envelope Q-Learning for Moving Decentralized Agents in Formation15 Oct

Other references · 22

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  3. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  4. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  5. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  6. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  7. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  8. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 270
  9. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
  10. 2021Trust Region Policy Optimisation in Multi-Agent Reinforcement Learningcited by 186
  11. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 122
  12. 2019Deep Coordination Graphscited by 98
10 more
  1. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 60
  2. 2021Context-Aware Sparse Deep Coordination Graphscited by 28
  3. 2024A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guidecited by 23
  4. 2024Group-Aware Coordination Graph for Multi-Agent Reinforcement Learningcited by 18
  5. 2021Self-Organized Polynomial-Time Coordination Graphscited by 15
  6. 2023Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learningcited by 8
  7. 2024Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learningcited by 7
  8. 2024MAexp: A Generic Platform for RL-based Multi-Agent Explorationcited by 7
  9. 2022Efficient Policy Generation in Multi-Agent Systems via Hypergraph Neural Networkcited by 4
  10. 2021Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolutioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfindingcited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2024Hypergraph-based Coordinated Task Allocation and Socially-aware Navigation for Multi-Robot Systems ↗
  2. 2025Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination
  3. 2024Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation
  4. 2025HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
  5. 2024Graph Neural Network-based Multi-agent Reinforcement Learning for Resilient Distributed Coordination of Multi-Robot Systems
  6. 2024Scaling Team Coordination on Graphs with Reinforcement Learning
  7. 2019Learning to Dynamically Coordinate Multi-Robot Teams in Graph Attention Networks
  8. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks