mlsanityData to 7 Oct 2026

MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence

arXiv 1712.00600 ↗First posted 2 Dec 2017cs.LG cs.AI cs.MAcited by 69

Not on the map. Why?

Abstract (arXiv)

We introduce MAgent, a platform to support research and development of many-agent reinforcement learning. Unlike previous research platforms on single or multi-agent reinforcement learning, MAgent focuses on supporting the tasks and the applications that require hundreds to millions of agents. Within the interactions among a population of agents, it enables not only the study of learning algorithms for agents' optimal polices, but more importantly, the observation and understanding of individual agent's behaviors and social phenomena emerging from the AI society, including communication languages, leaderships, altruism. MAgent is highly scalable and can host up to one million agents on a single GPU server. MAgent also provides flexible configurations for AI researchers to design their customized environments and agents. In this demo, we present three environments designed on MAgent and show emerged collective intelligence by learning from scratch.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 18; 2023: 14; 2024: 7; 2025: 13; 2026: 7.

69 papers.

Sort:

By area:

  1. 2021Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificatescited by 71
  2. 2022VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learningcited by 63
  3. 2021UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformerscited by 39
  4. 2022Multi-agent Dynamic Algorithm Configurationcited by 36
  5. 2023Multi-agent Reinforcement Learning: A Comprehensive Surveycited by 30
  6. 2022MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Librarycited by 21
  7. 2024POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfindingcited by 20
  8. 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Makingcited by 19
  9. 2021Collaborative Visual Navigationcited by 18
  10. 2022Influencing Long-Term Behavior in Multiagent Reinforcement Learningcited by 18
  11. 2021The Neural MMO Platform for Massively Multiagent Researchcited by 17
  12. 2022An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobilitycited by 16
38 more
  1. 2022RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on statescited by 16
  2. 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learningcited by 13
  3. 2022A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learningcited by 12
  4. 2024Emergent Language: A Survey and Taxonomycited by 12
  5. 2022Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RLcited by 11
  6. 2022Individual-Level Inverse Reinforcement Learning for Mean Field Gamescited by 10
  7. 2022Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learningcited by 10
  8. 2022Concentration Network for Reinforcement Learning of Large-Scale Multi-Agent Systemscited by 7
  9. 2023Partially Observable Mean Field Multi-Agent Reinforcement Learning Based on Graph-Attentioncited by 7
  10. 2025Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learningcited by 7
  11. 2022POGEMA: Partially Observable Grid Environment for Multiple Agentscited by 6
  12. 2023Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behaviorcited by 6
  13. 2023Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Gamescited by 6
  14. 2025Rethinking Agent Design: From Top-Down Workflows to Bottom-Up Skill Evolutioncited by 6
  15. 2023XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Librarycited by 5
  16. 2025An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Taskscited by 5
  17. 2021Learning to Share in Multi-Agent Reinforcement Learningcited by 4
  18. 2026Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Webcited by 4
  19. 2023Emergent collective intelligence from massive-agent cooperation and competitioncited by 3
  20. 2023Artificial Collective Intelligence Engineering: a Survey of Concepts and Perspectivescited by 3
  21. 2023Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learningcited by 3
  22. 2022Toward multi-target self-organizing pursuit in a partially observable Markov gamecited by 2
  23. 2022Collective Intelligence for 2D Push Manipulations with Mobile Robotscited by 2
  24. 2023SEA: A Spatially Explicit Architecture for Multi-Agent Reinforcement Learningcited by 2
  25. 2023Seeking Next Layer Neurons' Attention for Error-Backpropagation-Like Training in a Multi-Agent Network Frameworkcited by 2
  26. 2021Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learningcited by 1
  27. 2021A Microscopic Pandemic Simulator for Pandemic Prediction Using Scalable Million-Agent Reinforcement Learningcited by 1
  28. 2021Soft Hierarchical Graph Recurrent Networks for Many-Agent Partially Observable Environmentscited by 1
  29. 2022A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learningcited by 1
  30. 2022Learning Heterogeneous Agent Cooperation via Multiagent League Trainingcited by 1
  31. 2023Diverse Policy Optimization for Structured Action Spacecited by 1
  32. 2024GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Criticcited by 1
  33. 2025Learning to Lead Themselves: Agentic AI in MAS using MARLcited by 1
  34. 2025The Emergence of Complex Behavior in Large-Scale Ecological Environmentscited by 1
  35. 2026Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agentscited by 1
  36. 2021The AI Arena: A Framework for Distributed Multi-Agent Reinforcement Learningcited by 0
  37. 2021Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Networkcited by 0
  38. 2022PooL: Pheromone-inspired Communication Framework forLarge Scale Multi-Agent Reinforcement Learningcited by 0

50 most cited of 69 All 69 (JSON)