mlsanityData to 7 Oct 2026

The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts

arXiv 2107.12254 ↗First posted 26 Jul 2021cs.RO cs.LG cs.MAcited by 4

Not on the map. Why?

Abstract (arXiv)

Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances. The use of learning-based methods in multi-robot planning holds great promise as it enables us to offload the online computational burden of expensive, yet optimal solvers, to an offline learning procedure. Simply put, the idea is to train a policy to copy an optimal pattern generated by a small-scale system, and then transfer that policy to much larger systems, in the hope that the learned strategy scales, while maintaining near-optimal performance. Yet, a number of issues impede us from leveraging this idea to its full potential. This blue-sky paper elaborates some of the key challenges that remain.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 38 of its 62 references that are in the map. First posted on arXiv 26 Jul 2021.

Builds on

38 of 62 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Graph Attention Networkscited by 8,854
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  5. 2016Generative Adversarial Imitation Learningcited by 1,576
  6. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  8. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  9. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  10. 2018Reinforcement Learning for Solving the Vehicle Routing Problemcited by 327
  11. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 308
  12. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 277
26 more
  1. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  2. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 171
  3. 2020When2com: Multi-Agent Perception via Communication Graph Groupingcited by 157
  4. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 138
  5. 2019Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learningcited by 90
  6. 2019Graph Neural Networks for Decentralized Multi-Robot Path Planningcited by 84
  7. 2017Coordinated Multi-Agent Imitation Learningcited by 70
  8. 2020Deep Drone Acrobaticscited by 66
  9. 2017Towards Generalization and Simplicity in Continuous Controlcited by 65
  10. 2019Deep Drone Racing: From Simulation to Reality with Domain Randomizationcited by 63
  11. 2019Learning Decentralized Controllers for Robot Swarms with Graph Neural Networkscited by 62
  12. 2020PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelongcited by 61
  13. 2020Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planningcited by 41
  14. 2020Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learningcited by 36
  15. 2018VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Controlcited by 34
  16. 2020The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learningcited by 28
  17. 2019Graph Policy Gradients for Large Scale Robot Controlcited by 27
  18. 2018Global overview of Imitation Learningcited by 16
  19. 2018Learning in POMDPs with Monte Carlo Tree Searchcited by 15
  20. 2020Gaussian Process Based Message Filtering for Robust Multi-Agent Cooperation in the Presence of Adversarial Communicationcited by 11
  21. 2021ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecturecited by 9
  22. 2019Multi-Vehicle Mixed-Reality Reinforcement Learning for Autonomous Multi-Lane Drivingcited by 6
  23. 2020Failure-Resilient Coverage Maximization with Multiple Robotscited by 3
  24. 2021ROS-NetSim: A Framework for the Integration of Robotic and Network Simulatorscited by 3
  25. 2018Redundant Robot Assignment on Graphs with Uncertain Edge Costscited by 2
  26. 2021Coding for Distributed Multi-Agent Reinforcement Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 0; 2024: 0; 2025: 2.

4 papers.

  1. 2021A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policiescited by 11
  2. 2025Graph Attention-Guided Search for Dense Multi-Agent Pathfindingcited by 5
  3. 2022Understandable Controller Extraction from Video Observations of Swarmscited by 1
  4. 2025Flow-Opt: Scalable Centralized Multi-Robot Trajectory Optimization with Flow Matching and Differentiable Optimizationcited by 0