Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 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

T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration (2401.10973v1)

Published 19 Jan 2024 in cs.MA and cs.LG

Abstract: Communication stands as a potent mechanism to harmonize the behaviors of multiple agents. However, existing works primarily concentrate on broadcast communication, which not only lacks practicality, but also leads to information redundancy. This surplus, one-fits-all information could adversely impact the communication efficiency. Furthermore, existing works often resort to basic mechanisms to integrate observed and received information, impairing the learning process. To tackle these difficulties, we propose Targeted and Trusted Multi-Agent Communication (T2MAC), a straightforward yet effective method that enables agents to learn selective engagement and evidence-driven integration. With T2MAC, agents have the capability to craft individualized messages, pinpoint ideal communication windows, and engage with reliable partners, thereby refining communication efficiency. Following the reception of messages, the agents integrate information observed and received from different sources at an evidence level. This process enables agents to collectively use evidence garnered from multiple perspectives, fostering trusted and cooperative behaviors. We evaluate our method on a diverse set of cooperative multi-agent tasks, with varying difficulties, involving different scales and ranging from Hallway, MPE to SMAC. The experiments indicate that the proposed model not only surpasses the state-of-the-art methods in terms of cooperative performance and communication efficiency, but also exhibits impressive generalization.

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 (34)
  1. Learning dexterous in-hand manipulation. The International Journal of Robotics Research, 39(1): 3–20.
  2. Tarmac: Targeted multi-agent communication. In International Conference on Machine Learning, 1538–1546.
  3. Dempster, A. P. 1967. Upper and Lower Probabilities Induced by a Multivalued Mapping. The Annals of Mathematical Statistics, 38(2): 325 – 339.
  4. Learning individually inferred communication for multi-agent cooperation. Advances in Neural Information Processing Systems, 33: 22069–22079.
  5. CARLA: An Open Urban Driving Simulator. In 1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, California, USA, November 13-15, 2017, Proceedings, volume 78 of Proceedings of Machine Learning Research, 1–16. PMLR.
  6. Learning to communicate with deep multi-agent reinforcement learning. Advances in neural information processing systems, 29.
  7. Efficient Multi-agent Communication via Self-supervised Information Aggregation. Advances in Neural Information Processing Systems, 35: 1020–1033.
  8. Learning attentional communication for multi-agent cooperation. In Advances in neural information processing systems, 7254–7264.
  9. Jsang, A. 2018. Subjective Logic: A formalism for reasoning under uncertainty. Springer Publishing Company, Incorporated.
  10. Learning to schedule communication in multi-agent reinforcement learning. arXiv preprint arXiv:1902.01554.
  11. Multi-agent actor-critic for mixed cooperative-competitive environments. In Advances in neural information processing systems, 6379–6390.
  12. Predictive Uncertainty Estimation via Prior Networks. In Bengio, S.; Wallach, H. M.; Larochelle, H.; Grauman, K.; Cesa-Bianchi, N.; and Garnett, R., eds., Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, 7047–7058.
  13. Ensemble Distribution Distillation. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net.
  14. Learning agent communication under limited bandwidth by message pruning. arXiv preprint arXiv:1912.05304.
  15. Multi-Agent Graph-Attention Communication and Teaming. In AAMAS, 964–973.
  16. Deep exploration via bootstrapped DQN. In Advances in neural information processing systems, 4026–4034.
  17. QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning. arXiv preprint arXiv:1803.11485.
  18. The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043.
  19. Evidential Deep Learning to Quantify Classification Uncertainty. In Bengio, S.; Wallach, H. M.; Larochelle, H.; Grauman, K.; Cesa-Bianchi, N.; and Garnett, R., eds., Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, 3183–3193.
  20. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science, 362(6419): 1140–1144.
  21. Mastering the game of go without human knowledge. nature, 550(7676): 354–359.
  22. Learning when to communicate at scale in multiagent cooperative and competitive tasks. arXiv preprint arXiv:1812.09755.
  23. Learning Multiagent Communication with Backpropagation. In Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS’16, 2252–2260. Red Hook, NY, USA: Curran Associates Inc. ISBN 9781510838819.
  24. Intrinsic Motivated Multi-Agent Communication. In Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS ’21, 1668–1670. Richland, SC: International Foundation for Autonomous Agents and Multiagent Systems. ISBN 9781450383073.
  25. Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296.
  26. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature, 575(7782): 350–354.
  27. Learning Efficient Multi-agent Communication: An Information Bottleneck Approach. In ICML 2020: 37th International Conference on Machine Learning.
  28. Learning Nearly Decomposable Value Functions Via Communication Minimization. In ICLR 2020 : Eighth International Conference on Learning Representations.
  29. Dop: Off-policy multi-agent decomposed policy gradients. In International Conference on Learning Representations.
  30. Efficient Multi-Agent Communication via Shapley Message Value. In Raedt, L. D., ed., Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, 578–584. International Joint Conferences on Artificial Intelligence Organization. Main Track.
  31. The surprising effectiveness of ppo in cooperative multi-agent games. Advances in Neural Information Processing Systems, 35: 24611–24624.
  32. Multi-agent incentive communication via decentralized teammate modeling. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 9466–9474.
  33. Efficient communication in multi-agent reinforcement learning via variance based control. In Advances in Neural Information Processing Systems, 3235–3244.
  34. Succinct and robust multi-agent communication with temporal message control. Advances in Neural Information Processing Systems, 33: 17271–17282.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Chuxiong Sun (13 papers)
  2. Zehua Zang (4 papers)
  3. Jiabao Li (3 papers)
  4. Jiangmeng Li (43 papers)
  5. Xiao Xu (81 papers)
  6. Rui Wang (996 papers)
  7. Changwen Zheng (60 papers)
Citations (5)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets