Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Context-aware Communication for Multi-agent Reinforcement Learning (2312.15600v3)

Published 25 Dec 2023 in cs.LG and cs.MA

Abstract: Effective communication protocols in multi-agent reinforcement learning (MARL) are critical to fostering cooperation and enhancing team performance. To leverage communication, many previous works have proposed to compress local information into a single message and broadcast it to all reachable agents. This simplistic messaging mechanism, however, may fail to provide adequate, critical, and relevant information to individual agents, especially in severely bandwidth-limited scenarios. This motivates us to develop context-aware communication schemes for MARL, aiming to deliver personalized messages to different agents. Our communication protocol, named CACOM, consists of two stages. In the first stage, agents exchange coarse representations in a broadcast fashion, providing context for the second stage. Following this, agents utilize attention mechanisms in the second stage to selectively generate messages personalized for the receivers. Furthermore, we employ the learned step size quantization (LSQ) technique for message quantization to reduce the communication overhead. To evaluate the effectiveness of CACOM, we integrate it with both actor-critic and value-based MARL algorithms. Empirical results on cooperative benchmark tasks demonstrate that CACOM provides evident performance gains over baselines under communication-constrained scenarios. The code is publicly available at https://github.com/LXXXXR/CACOM.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Asim Ansari and Carl F Mela. 2003. E-customization. Journal of marketing research 40, 2 (2003), 131–145.
  2. Tarmac: Targeted multi-agent communication. In International Conference on Machine Learning. PMLR, 1538–1546.
  3. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248–255.
  4. Learning individually inferred communication for multi-agent cooperation. Advances in Neural Information Processing Systems 33 (2020), 22069–22079.
  5. Learned Step Size Quantization. In International Conference on Learning Representations.
  6. Learning to communicate with deep multi-agent reinforcement learning. Advances in neural information processing systems 29 (2016).
  7. Efficient Multi-agent Communication via Self-supervised Information Aggregation. Advances in Neural Information Processing Systems 35 (2022), 1020–1033.
  8. Model-based Sparse Communication in Multi-agent Reinforcement Learning. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. 439–447.
  9. Event-triggered communication network with limited-bandwidth constraint for multi-agent reinforcement learning. IEEE Transactions on Neural Networks and Learning Systems (2021).
  10. Distributed consensus of multi-agent systems over general directed networks with limited bandwidth communication. Neurocomputing 174 (2016), 681–688.
  11. Graph Convolutional Reinforcement Learning. In International Conference on Learning Representations.
  12. Jiechuan Jiang and Zongqing Lu. 2018. Learning attentional communication for multi-agent cooperation. Advances in neural information processing systems 31 (2018).
  13. Landon Kraemer and Bikramjit Banerjee. 2016. Multi-agent reinforcement learning as a rehearsal for decentralized planning. Neurocomputing 190 (2016), 82–94.
  14. Tailoring health messages: Customizing communication with computer technology. Routledge.
  15. Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning. In Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems. 764–772.
  16. Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization. arXiv:2202.01334 [cs.LG]
  17. Multi-agent game abstraction via graph attention neural network. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 7211–7218.
  18. Multi-agent actor-critic for mixed cooperative-competitive environments. Advances in neural information processing systems 30 (2017).
  19. Contrasting centralized and decentralized critics in multi-agent reinforcement learning. arXiv preprint arXiv:2102.04402 (2021).
  20. Frans A Oliehoek and Christopher Amato. 2016. A concise introduction to decentralized POMDPs. Springer.
  21. Afshin Oroojlooy and Davood Hajinezhad. 2022. A review of cooperative multi-agent deep reinforcement learning. Applied Intelligence (2022), 1–46.
  22. Exploiting spatial locality and heterogeneity of agents for search and rescue teamwork. Journal of Field Robotics 33, 7 (2016), 877–900.
  23. Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games. arXiv preprint arXiv:1703.10069 (2017).
  24. Monotonic value function factorisation for deep multi-agent reinforcement learning. The Journal of Machine Learning Research 21, 1 (2020), 7234–7284.
  25. The StarCraft Multi-Agent Challenge. CoRR abs/1902.04043 (2019).
  26. Sven Seuken and Shlomo Zilberstein. 2007. Improved memory-bounded dynamic programming for decentralized POMDPs. In Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence. 344–351.
  27. Individualized controlled continuous communication model for multiagent cooperative and competitive tasks. In International conference on learning representations.
  28. Learning multiagent communication with backpropagation. Advances in neural information processing systems 29 (2016).
  29. Scaled autonomy: Enabling human operators to control robot fleets. In 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 5942–5948.
  30. Learning nearly decomposable value functions via communication minimization. arXiv preprint arXiv:1910.05366 (2019).
  31. Tom2c: Target-oriented multi-agent communication and cooperation with theory of mind. arXiv preprint arXiv:2111.09189 (2021).
  32. Wang Ying and Sang Dayong. 2005. Multi-agent framework for third party logistics in E-commerce. Expert Systems with Applications 29, 2 (2005), 431–436.
  33. The surprising effectiveness of ppo in cooperative, multi-agent games. arXiv preprint arXiv:2103.01955 (2021).
  34. Multi-agent incentive communication via decentralized teammate modeling. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 9466–9474.
  35. Efficient communication in multi-agent reinforcement learning via variance based control. Advances in Neural Information Processing Systems 32 (2019).
  36. Succinct and robust multi-agent communication with temporal message control. Advances in Neural Information Processing Systems 33 (2020), 17271–17282.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Xinran Li (71 papers)
  2. Jun Zhang (1008 papers)
Citations (4)
View on Semantic Scholar
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - LXXXXR/CACOM: Code for "Context-aware Communication for Multi-agent Reinforcement Learning" (14 stars)