mlsanityData to 14 Oct 2026

Communication-Enhanced Tutoring for Efficient Decentralized Multi-Agent Reinforcement Learning

arXiv 2508.13661 ↗First posted 19 Aug 2025cs.LG cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

Centralized Training with Decentralized Execution (CTDE) is the dominant paradigm in multi-agent reinforcement learning (MARL), enabling agents to act independently at test time while leveraging additional information during training. However, the most prominent methods within CTDE, based on value decomposition, are limited in learning efficiency and final performance by partial observability in both training and execution. To overcome this limitation, in this work, we propose the framework of tutoring: In training, the agents share information in their latent space to develop well-informed policies that achieve strong performance. Then, to recover decentralized execution, these policies concurrently adjust to anticipate lack of communication, and they are distilled into counterparts that rely solely on local observations. We demonstrate the effectiveness of our approach on Hallway, which, to the best of our knowledge, has not been solved before without test-time communication, SMAC under settings more difficult than the standard ones, and SMACv2.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 19 Aug 2025.

Builds on

29 of 44 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  5. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  6. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  7. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  8. 2019The StarCraft Multi-Agent Challengecited by 597
  9. 2019Learning by Cheatingcited by 383
  10. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
  11. 2016Learning Multiagent Communication with Backpropagationcited by 366
  12. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 270
17 more
  1. 2024Reinforcement learningcited by 247
  2. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
  3. 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
  4. 2022Multi-Agent Reinforcement Learning is a Sequence Modeling Problemcited by 155
  5. 2018Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applicationscited by 127
  6. 2021Celebrating Diversity in Shared Multi-Agent Reinforcement Learningcited by 98
  7. 2019Learning Nearly Decomposable Value Functions Via Communication Minimizationcited by 86
  8. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 82
  9. 2020Qatten: A General Framework for Cooperative Multiagent Reinforcement Learningcited by 81
  10. 2020Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorialcited by 60
  11. 2024Learning Multi-Agent Communication from Graph Modeling Perspectivecited by 48
  12. 2020Bridging the Imitation Gap by Adaptive Insubordinationcited by 38
  13. 2021Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Surveycited by 34
  14. 2021SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learningcited by 26
  15. 2020Robust Asymmetric Learning in POMDPscited by 23
  16. 2024Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Modelscited by 10
  17. 2023Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanismcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning
  2. 2022Scalable Multi-Agent Model-Based Reinforcement Learning
  3. 2024An Initial Introduction to Cooperative Multi-Agent Reinforcement Learning
  4. 2019Decentralized Multi-Agents by Imitation of a Centralized Controller
  5. 2025A Communication-Efficient Decentralized Actor-Critic Algorithm
  6. 2024Tacit Learning with Adaptive Information Selection for Cooperative Multi-Agent Reinforcement Learning
  7. 2025Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning
  8. 2024Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey