# SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding

arXiv: https://arxiv.org/abs/2303.00605 · HTML: https://mlsanity.com/paper/2303.00605/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2023.

## Built on by (most cited first, 30 of 37)

- [Learn to Follow: Decentralized Lifelong Multi-agent Pathfinding via Planning and Learning](https://mlsanity.com/paper/2310.01207/) (2023)
- [POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding](https://mlsanity.com/paper/2407.14931/) (2024)
- [MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale](https://mlsanity.com/paper/2409.00134/) (2024)
- [Improving Learnt Local MAPF Policies with Heuristic Search](https://mlsanity.com/paper/2403.20300/) (2024)
- [Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding](https://mlsanity.com/paper/2312.15908/) (2023)
- [Work Smarter Not Harder: Simple Imitation Learning with CS-PIBT Outperforms Large Scale Imitation Learning for MAPF](https://mlsanity.com/paper/2409.14491/) (2024)
- [SRMT: Shared Memory for Multi-agent Lifelong Pathfinding](https://mlsanity.com/paper/2501.13200/) (2025)
- [Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding](https://mlsanity.com/paper/2403.07559/) (2024)
- [Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding](https://mlsanity.com/paper/2410.21415/) (2024)
- [Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding](https://mlsanity.com/paper/2308.05893/) (2023)
- [RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks](https://mlsanity.com/paper/2503.02992/) (2025)
- [Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning](https://mlsanity.com/paper/2506.23793/) (2025)
- [Graph Attention-Guided Search for Dense Multi-Agent Pathfinding](https://mlsanity.com/paper/2510.17382/) (2025)
- [HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent Pathfinding](https://mlsanity.com/paper/2402.15546/) (2024)
- [SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding](https://mlsanity.com/paper/2502.06440/) (2025)
- [DeepFleet: Multi-Agent Foundation Models for Mobile Robots](https://mlsanity.com/paper/2508.08574/) (2025)
- [Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding](https://mlsanity.com/paper/2602.06733/) (2026)
- [Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning](https://mlsanity.com/paper/2605.27697/) (2026)
- [QD-MAPPER: A Quality Diversity Framework to Automatically Evaluate Multi-Agent Path Finding Algorithms in Diverse Maps](https://mlsanity.com/paper/2409.06888/) (2024)
- [MFC-EQ: Mean-Field Control with Envelope Q-Learning for Moving Decentralized Agents in Formation](https://mlsanity.com/paper/2410.12062/) (2024)
- [Towards Robust Multi-UAV Collaboration: MARL with Noise-Resilient Communication and Attention Mechanisms](https://mlsanity.com/paper/2503.02913/) (2025)
- [Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding](https://mlsanity.com/paper/2605.07637/) (2026)
- [Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention](https://mlsanity.com/paper/2605.13296/) (2026)
- [Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations](https://mlsanity.com/paper/2608.05588/) (2026)
- [State-of-the-art in Robot Learning for Multi-Robot Collaboration: A Comprehensive Survey](https://mlsanity.com/paper/2408.11822/) (2024)
- [Multi-Robot Reliable Navigation in Uncertain Topological Environments with Graph Attention Networks](https://mlsanity.com/paper/2411.16134/) (2024)
- [MAPF-World: Action World Model for Multi-Agent Path Finding](https://mlsanity.com/paper/2508.12087/) (2025)
- [Multi-Agent Path Finding via Offline RL and LLM Collaboration](https://mlsanity.com/paper/2509.22130/) (2025)
- [Sequence Pathfinder for Multi-Agent Pickup and Delivery in the Warehouse](https://mlsanity.com/paper/2509.23778/) (2025)
- [Towards Information-Optimized Multi-Agent Path Finding: A Hybrid Framework with Reduced Inter-Agent Information Sharing](https://mlsanity.com/paper/2510.09469/) (2025)

## Abstract (arXiv)

Trading off performance guarantees in favor of scalability, the Multi-Agent Path Finding (MAPF) community has recently started to embrace Multi-Agent Reinforcement Learning (MARL), where agents learn to collaboratively generate individual, collision-free (but often suboptimal) paths. Scalability is usually achieved by assuming a local field of view (FOV) around the agents, helping scale to arbitrary world sizes. However, this assumption significantly limits the amount of information available to the agents, making it difficult for them to enact the type of joint maneuvers needed in denser MAPF tasks. In this paper, we propose SCRIMP, where agents learn individual policies from even very small (down to 3x3) FOVs, by relying on a highly-scalable global/local communication mechanism based on a modified transformer. We further equip agents with a state-value-based tie-breaking strategy to further improve performance in symmetric situations, and introduce intrinsic rewards to encourage exploration while mitigating the long-term credit assignment problem. Empirical evaluations on a set of experiments indicate that SCRIMP can achieve higher performance with improved scalability compared to other state-of-the-art learning-based MAPF planners with larger FOVs, and even yields similar performance as a classical centralized planner in many cases. Ablation studies further validate the effectiveness of our proposed techniques. Finally, we show that our trained model can be directly implemented on real robots for online MAPF through high-fidelity simulations in gazebo.