mlsanityData to 7 Oct 2026

Consensus Learning for Cooperative Multi-Agent Reinforcement Learning

arXiv 2206.02583 ↗First posted 6 Jun 2022cs.MA cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During centralized training, agents can be guided by the same signals, such as the global state. During decentralized execution, however, agents lack the shared signal. Inspired by viewpoint invariance and contrastive learning, we propose consensus learning for cooperative multi-agent reinforcement learning in this paper. Although based on local observations, different agents can infer the same consensus in discrete space. During decentralized execution, we feed the inferred consensus as an explicit input to the network of agents, thereby developing their spirit of cooperation. Our proposed method can be extended to various multi-agent reinforcement learning algorithms with small model changes. Moreover, we carry out them on some fully cooperative tasks and get convincing results.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 45 of its 55 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

45 of 55 references.

References · 45

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  8. 2020Supervised Contrastive Learningcited by 2,803
  9. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  10. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  11. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  12. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
33 more
  1. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  2. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  3. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  4. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  5. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  6. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  7. 2019The StarCraft Multi-Agent Challengecited by 589
  8. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  9. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  10. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
  11. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  12. 2020Reinforcement Learning with Augmented Datacited by 452
  13. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 372
  14. 2016Learning Multiagent Communication with Backpropagationcited by 355
  15. 2020Data-Efficient Reinforcement Learning with Self-Predictive Representationscited by 309
  16. 2019Google Research Football: A Novel Reinforcement Learning Environmentcited by 257
  17. 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
  18. 2019MAVEN: Multi-Agent Variational Explorationcited by 181
  19. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 170
  20. 2016On Deep Multi-View Representation Learning: Objectives and Optimizationcited by 162
  21. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 159
  22. 2013A Survey on Multi-view Learningcited by 152
  23. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 135
  24. 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
  25. 2019CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenariocited by 114
  26. 2018Unsupervised Control Through Non-Parametric Discriminative Rewardscited by 102
  27. 2017Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Gamescited by 93
  28. 2019Learning to Schedule Communication in Multi-agent Reinforcement Learningcited by 89
  29. 2018Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networkscited by 70
  30. 2020Social NCE: Contrastive Learning of Socially-aware Motion Representationscited by 58
  31. 2020On Mutual Information in Contrastive Learning for Visual Representationscited by 54
  32. 2018Learning Actionable Representations from Visual Observationscited by 35
  33. 2022Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 1; 2025: 1; 2026: 2.

8 papers.

  1. 2023Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approachcited by 38
  2. 2023Advances in Embodied Navigation Using Large Language Models: A Surveycited by 14
  3. 2024Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Taskscited by 12
  4. 2023From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARLcited by 11
  5. 2023MAHTM: A Multi-Agent Framework for Hierarchical Transactive Microgridscited by 3
  6. 2025Decentralized Consensus Inference-based Hierarchical Reinforcement Learning for Multi-Constrained UAV Pursuit-Evasion Gamecited by 2
  7. 2026LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learningcited by 2
  8. 2026CCKS: Consensus-based Communication and Knowledge Sharingcited by 0