mlsanityData to 14 Oct 2026

TarMAC: Targeted Multi-Agent Communication

arXiv 1810.11187 ↗First posted 26 Oct 2018cs.LG cs.AI cs.MAcited by 208

Not on the map. Why?

Abstract (arXiv)

We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This targeting behavior is learnt solely from downstream task-specific reward without any communication supervision. We additionally augment this with a multi-round communication approach where agents coordinate via multiple rounds of communication before taking actions in the environment. We evaluate our approach on a diverse set of cooperative multi-agent tasks, of varying difficulties, with varying number of agents, in a variety of environments ranging from 2D grid layouts of shapes and simulated traffic junctions to 3D indoor environments, and demonstrate the benefits of targeted and multi-round communication. Moreover, we show that the targeted communication strategies learned by agents are interpretable and intuitive. Finally, we show that our architecture can be easily extended to mixed and competitive environments, leading to improved performance and sample complexity over recent state-of-the-art approaches.

Key facts. Cited by 208 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 30; 2022: 35; 2023: 42; 2024: 19; 2025: 17; 2026: 65.

208 papers.

Sort:

By area:

  1. 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 237
  2. 2021Learning Distilled Collaboration Graph for Multi-Agent Perceptioncited by 194
  3. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 175
  4. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 104
  5. 2023Collaborative Perception in Autonomous Driving: Methods, Datasets and Challengescited by 87
  6. 2024Embodied LLM Agents Learn to Cooperate in Organized Teamscited by 82
  7. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directionscited by 67
  8. 2021ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mindcited by 58
  9. 2021Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learningcited by 56
  10. 2021Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)cited by 55
  11. 2023Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perceptioncited by 52
  12. 2022Towards a Standardised Performance Evaluation Protocol for Cooperative MARLcited by 49
38 more
  1. 2024Learning Multi-Agent Communication from Graph Modeling Perspectivecited by 48
  2. 2021Learning to Ground Multi-Agent Communication with Autoencoderscited by 37
  3. 2025Multi-Agent Coordination across Diverse Applications: A Surveycited by 37
  4. 2022Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregationcited by 36
  5. 2021Offline Decentralized Multi-Agent Reinforcement Learningcited by 33
  6. 2021Distributed Heuristic Multi-Agent Path Finding with Communicationcited by 32
  7. 2021Learning Selective Communication for Multi-Agent Path Findingcited by 32
  8. 2022AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistantcited by 32
  9. 2022A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learningcited by 31
  10. 2023A Review of Cooperation in Multi-agent Learningcited by 29
  11. 2022Scalable Multi-Agent Model-Based Reinforcement Learningcited by 25
  12. 2021Learning to Draw: Emergent Communication through Sketchingcited by 23
  13. 2021Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agentscited by 19
  14. 2021Emergent Communication under Competitioncited by 18
  15. 2021Collaborative Visual Navigationcited by 18
  16. 2021Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learningcited by 18
  17. 2021Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learningcited by 18
  18. 2023Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?cited by 18
  19. 2021Causal Multi-Agent Reinforcement Learning: Review and Open Problemscited by 16
  20. 2022Distributed Reinforcement Learning for Robot Teams: A Reviewcited by 16
  21. 2021Self-Organized Polynomial-Time Coordination Graphscited by 15
  22. 2022Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teamingcited by 14
  23. 2022QGNN: Value Function Factorisation with Graph Neural Networkscited by 14
  24. 2022A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learningcited by 14
  25. 2022Multi-Agent Coordination via Multi-Level Communicationcited by 14
  26. 2021Neurosymbolic Transformers for Multi-Agent Communicationcited by 13
  27. 2023Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learningcited by 13
  28. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 13
  29. 2023Context-aware Communication for Multi-agent Reinforcement Learningcited by 13
  30. 2022Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradientscited by 12
  31. 2021Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learningcited by 11
  32. 2022Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantizationcited by 11
  33. 2023From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARLcited by 11
  34. 2021Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid Worldcited by 10
  35. 2021Communicating via Markov Decision Processescited by 10
  36. 2021Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledgecited by 10
  37. 2022Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learningcited by 10
  38. 2024T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integrationcited by 10

50 most cited of 208 All 208 (JSON)