mlsanityData to 7 Oct 2026

LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates

arXiv 2109.12508 ↗First posted 26 Sep 2021cs.LG cs.MAcited by 9

Not on the map. Why?

Abstract (arXiv)

In cooperative multi-agent reinforcement learning (MARL), where agents only have access to partial observations, efficiently leveraging local information is critical. During long-time observations, agents can build textitawareness for teammates to alleviate the problem of partial observability. However, previous MARL methods usually neglect this kind of utilization of local information. To address this problem, we propose a novel framework, multi-agent textitLocal INformation Decomposition for Awareness of teammates (LINDA), with which agents learn to decompose local information and build awareness for each teammate. We model the awareness as stochastic random variables and perform representation learning to ensure the informativeness of awareness representations by maximizing the mutual information between awareness and the actual trajectory of the corresponding agent. LINDA is agnostic to specific algorithms and can be flexibly integrated to different MARL methods. Sufficient experiments show that the proposed framework learns informative awareness from local partial observations for better collaboration and significantly improves the learning performance, especially on challenging tasks.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 33 of its 52 references that are in the map. First posted on arXiv 26 Sep 2021.

Builds on

33 of 52 references.

References · 33

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  3. 2016Deep Variational Information Bottleneckcited by 915
  4. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  5. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  6. 2019The StarCraft Multi-Agent Challengecited by 589
  7. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
  8. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 372
  9. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
  10. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 267
  11. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 259
  12. 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
21 more
  1. 2019A Review of Cooperative Multi-Agent Deep Reinforcement Learningcited by 147
  2. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 135
  3. 2017Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problemscited by 126
  4. 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
  5. 2020SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Drivingcited by 121
  6. 2020Shared Experience Actor-Critic for Multi-Agent Reinforcement Learningcited by 114
  7. 2016Opponent Modeling in Deep Reinforcement Learningcited by 94
  8. 2020Learning Latent Representations to Influence Multi-Agent Interactioncited by 92
  9. 2019Learning Nearly Decomposable Value Functions Via Communication Minimizationcited by 85
  10. 2019Shapley Q-value: A Local Reward Approach to Solve Global Reward Gamescited by 71
  11. 2021Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learningcited by 54
  12. 2019Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learningcited by 53
  13. 2021UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformerscited by 39
  14. 2021Context-Aware Sparse Deep Coordination Graphscited by 27
  15. 2017A Deep Policy Inference Q-Network for Multi-Agent Systemscited by 24
  16. 2019Reasoning about Hypothetical Agent Behaviours and their Parameterscited by 24
  17. 2019Action Semantics Network: Considering the Effects of Actions in Multiagent Systemscited by 19
  18. 2020Variational Autoencoders for Opponent Modeling in Multi-Agent Systemscited by 18
  19. 2020Multi-Agent Collaboration via Reward Attribution Decompositioncited by 17
  20. 2021Survey of Recent Multi-Agent Reinforcement Learning Algorithms Utilizing Centralized Trainingcited by 16
  21. 2018Hierarchical Macro Strategy Model for MOBA Game AIcited by 12

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4; 2024: 2.

9 papers.

  1. 2022Multi-Agent Policy Transfer via Task Relationship Modelingcited by 14
  2. 2023Multi-agent Continual Coordination via Progressive Task Contextualizationcited by 10
  3. 2023Self-Motivated Multi-Agent Explorationcited by 7
  4. 2024Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharingcited by 6
  5. 2024A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocationcited by 6
  6. 2023Robust Multi-agent Communication via Multi-view Message Certificationcited by 3
  7. 2022A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learningcited by 1
  8. 2022Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learningcited by 1
  9. 2023Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learningcited by 1