mlsanityData to 7 Oct 2026

Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

arXiv 2211.02127 ↗First posted 3 Nov 2022cs.MA cs.AI cs.ROcited by 34

Not on the map. Why?

Abstract (arXiv)

We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which uses local information intelligently to compute paths for all the agents in a decentralized manner. Specifically, InforMARL aggregates information about the local neighborhood of agents for both the actor and the critic using a graph neural network and can be used in conjunction with any standard MARL algorithm. We show that (1) in training, InforMARL has better sample efficiency and performance than baseline approaches, despite using less information, and (2) in testing, it scales well to environments with arbitrary numbers of agents and obstacles. We illustrate these results using four task environments, including one with predetermined goals for each agent, and one in which the agents collectively try to cover all goals. Code available at https://github.com/nsidn98/InforMARL.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 35 of its 68 references that are in the map. First posted on arXiv 3 Nov 2022.

Builds on

35 of 68 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2015Continuous control with deep reinforcement learningcited by 3,279
  7. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  9. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  10. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  11. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  12. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
23 more
  1. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  2. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  3. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  4. 2020A Generalization of Transformer Networks to Graphscited by 653
  5. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  6. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
  7. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 457
  8. 2016Learning Multiagent Communication with Backpropagationcited by 355
  9. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  10. 2018TarMAC: Targeted Multi-Agent Communicationcited by 201
  11. 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 180
  12. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 170
  13. 2015Learning Continuous Control Policies by Stochastic Value Gradientscited by 156
  14. 2018Graph Convolutional Reinforcement Learningcited by 148
  15. 2018Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysiscited by 110
  16. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 81
  17. 2021Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificatescited by 71
  18. 2017VAIN: Attentional Multi-agent Predictive Modelingcited by 51
  19. 2019Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Criticscited by 46
  20. 2019Learning Transferable Cooperative Behavior in Multi-Agent Teamscited by 40
  21. 2019Graph Policy Gradients for Large Scale Robot Controlcited by 27
  22. 2016Vehicle Routing Problems for Drone Deliverycited by 23
  23. 2021Attention-based Reinforcement Learning for Real-Time UAV Semantic Communicationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 20; 2026: 9.

34 papers.

Sort:

By area:

  1. 2023Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?cited by 18
  2. 2025SRMT: Shared Memory for Multi-agent Lifelong Pathfindingcited by 8
  3. 2025Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Controlcited by 7
  4. 2024Cooperation and Fairness in Multi-Agent Reinforcement Learningcited by 5
  5. 2024Crafting Desirable Climate Trajectories with RL Explored Socio-Environmental Simulationscited by 4
  6. 2025Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARLcited by 4
  7. 2025Shapley Machine: A Game-Theoretic Framework for N-Agent Ad Hoc Teamworkcited by 4
  8. 2023Decentralized Multi-Agent Reinforcement Learning with Global State Predictioncited by 3
  9. 2025Contextual Knowledge Sharing in Multi-Agent Reinforcement Learning with Decentralized Communication and Coordinationcited by 2
  10. 2025Robust Noise Attenuation via Adaptive Pooling of Transformer Outputscited by 2
  11. 2025Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learningcited by 2
  12. 2025Symmetries-enhanced Multi-Agent Reinforcement Learningcited by 1
22 more
  1. 2025Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learningcited by 1
  2. 2025Optimization without Future Compromises? Decentralized Coordination via Collective and Reinforcement Learningcited by 1
  3. 2025Multi-Agent Conditional Diffusion Model with Mean Field Communication as Wireless Resource Allocation Plannercited by 1
  4. 2026Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulationcited by 1
  5. 2023Optimizing Crowd-Aware Multi-Agent Path Finding through Local Communication with Graph Neural Networkscited by 0
  6. 2025Scalable Safe Multi-Agent Reinforcement Learning for Multi-Agent Systemcited by 0
  7. 2025Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehiclescited by 0
  8. 2025LOD: Latent Objective Discovery in Heterogeneous Multi-Agent Reinforcement Learningcited by 0
  9. 2025ReCoDe: Reinforcement Learning-based Dynamic Constraint Design for Multi-Agent Coordinationcited by 0
  10. 2025MAD-PINN: A Decentralized Physics-Informed Machine Learning Framework for Safe and Optimal Multi-Agent Controlcited by 0
  11. 2025Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspectivecited by 0
  12. 2025Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teamscited by 0
  13. 2025Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policiescited by 0
  14. 2025Inter-Agent Relative Representations for Multi-Agent Option Discoverycited by 0
  15. 2026Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learningcited by 0
  16. 2026Communication Gain and Delay Cost Under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learningcited by 0
  17. 2026SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learningcited by 0
  18. 2026Decentralized Autonomous Traffic Management through Corridor Networkscited by 0
  19. 2026Decentralized Coordination of Autonomous Traffic Through Advanced Air Mobility Corridorscited by 0
  20. 2026Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Controlcited by 0
  21. 2026Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuningcited by 0
  22. 2026DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communicationcited by 0