# Learning Selective Communication for Multi-Agent Path Finding

arXiv: https://arxiv.org/abs/2109.05413 · HTML: https://mlsanity.com/paper/2109.05413/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 12 Sep 2021.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [Distributed Prioritized Experience Replay](https://mlsanity.com/paper/1803.00933/) (2018)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks](https://mlsanity.com/paper/1906.08291/) (2019)
- [Graph Convolutional Reinforcement Learning](https://mlsanity.com/paper/1810.09202/) (2018)
- [Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks](https://mlsanity.com/paper/1812.09755/) (2018)
- [Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning](https://mlsanity.com/paper/1805.01956/) (2018)
- [Learning to Schedule Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1902.01554/) (2019)
- [PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning](https://mlsanity.com/paper/1809.03531/) (2018)
- [Learning Nearly Decomposable Value Functions Via Communication Minimization](https://mlsanity.com/paper/1910.05366/) (2019)
- [Graph Neural Networks for Decentralized Multi-Robot Path Planning](https://mlsanity.com/paper/1912.06095/) (2019)
- [PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelong](https://mlsanity.com/paper/2010.08184/) (2020)
- [Learning Individually Inferred Communication for Multi-Agent Cooperation](https://mlsanity.com/paper/2006.06455/) (2020)
- [Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control](https://mlsanity.com/paper/1909.02682/) (2019)
- [Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning](https://mlsanity.com/paper/2011.13219/) (2020)
- [Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning](https://mlsanity.com/paper/2005.05420/) (2020)
- [Distributed Heuristic Multi-Agent Path Finding with Communication](https://mlsanity.com/paper/2106.11365/) (2021)
- [Succinct and Robust Multi-Agent Communication With Temporal Message Control](https://mlsanity.com/paper/2010.14391/) (2020)
- [MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments](https://mlsanity.com/paper/2007.15724/) (2020)
- [GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning with End-to-End Learning](https://mlsanity.com/paper/2002.11807/) (2020)

## Built on by (most cited first, 30 of 32)

- [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)
- [Distributed Reinforcement Learning for Robot Teams: A Review](https://mlsanity.com/paper/2204.03516/) (2022)
- [Vehicle-to-Everything Cooperative Perception for Autonomous Driving](https://mlsanity.com/paper/2310.03525/) (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)
- [Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message Passing](https://mlsanity.com/paper/2402.05027/) (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)
- [SACHA: Soft Actor-Critic with Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding](https://mlsanity.com/paper/2307.02691/) (2023)
- [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)
- [Selective Communication for Cooperative Perception in End-to-End Autonomous Driving](https://mlsanity.com/paper/2305.17181/) (2023)
- [Robust Communicative Multi-Agent Reinforcement Learning with Active Defense](https://mlsanity.com/paper/2312.11545/) (2023)
- [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)
- [Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding](https://mlsanity.com/paper/2602.06733/) (2026)
- [MFC-EQ: Mean-Field Control with Envelope Q-Learning for Moving Decentralized Agents in Formation](https://mlsanity.com/paper/2410.12062/) (2024)
- [SkyRover: A Modular Simulator for Cross-Domain Pathfinding](https://mlsanity.com/paper/2502.08969/) (2025)
- [LLMDR: LLM-Driven Deadlock Detection and Resolution in Multi-Agent Pathfinding](https://mlsanity.com/paper/2503.00717/) (2025)
- [Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding](https://mlsanity.com/paper/2605.07637/) (2026)
- [Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations](https://mlsanity.com/paper/2608.05588/) (2026)
- [Low Entropy Communication in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2302.05055/) (2023)
- [Cooperative Reward Shaping for Multi-Agent Pathfinding](https://mlsanity.com/paper/2407.10403/) (2024)
- [Improving Zero-Shot ObjectNav with Generative Communication](https://mlsanity.com/paper/2408.01877/) (2024)
- [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)

Learning communication via deep reinforcement learning (RL) or imitation learning (IL) has recently been shown to be an effective way to solve Multi-Agent Path Finding (MAPF). However, existing communication based MAPF solvers focus on broadcast communication, where an agent broadcasts its message to all other or predefined agents. It is not only impractical but also leads to redundant information that could even impair the multi-agent cooperation. A succinct communication scheme should learn which information is relevant and influential to each agent's decision making process. To address this problem, we consider a request-reply scenario and propose Decision Causal Communication (DCC), a simple yet efficient model to enable agents to select neighbors to conduct communication during both training and execution. Specifically, a neighbor is determined as relevant and influential only when the presence of this neighbor causes the decision adjustment on the central agent. This judgment is learned only based on agent's local observation and thus suitable for decentralized execution to handle large scale problems. Empirical evaluation in obstacle-rich environment indicates the high success rate with low communication overhead of our method.