Corpus ID: 208139009

Learning Efficient Multi-agent Communication: An Information Bottleneck Approach

@article{Wang2020LearningEM,
  title={Learning Efficient Multi-agent Communication: An Information Bottleneck Approach},
  author={R. Wang and Xu He and Runsheng Yu and Wei Qiu and Bo An and Zinovi Rabinovich},
  journal={ArXiv},
  year={2020},
  volume={abs/1911.06992}
}
We consider the problem of the limited-bandwidth communication for multi-agent reinforcement learning, where agents cooperate with the assistance of a communication protocol and a scheduler. The protocol and scheduler jointly determine which agent is communicating what message and to whom. Under the limited bandwidth constraint, a communication protocol is required to generate informative messages. Meanwhile, an unnecessary communication connection should not be established because it occupies… Expand
11 Citations
Event-Triggered Communication Network with Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning
  • 2020
  • Highly Influenced
Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication
  • 1
  • PDF
Graph Information Bottleneck for Subgraph Recognition
  • 1
  • PDF
Recognizing Predictive Substructures with Subgraph Information Bottleneck
  • PDF
MetaInfoNet: Learning Task-Guided Information for Sample Reweighting
  • PDF
Intrinsic Motivated Multi-Agent Communication
  • Chuxiong Sun
  • 2021
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 45 REFERENCES
Learning Multi-agent Communication under Limited-bandwidth Restriction for Internet Packet Routing
  • 6
  • Highly Influential
  • PDF
Learning to Schedule Communication in Multi-agent Reinforcement Learning
  • 42
  • Highly Influential
  • PDF
TarMAC: Targeted Multi-Agent Communication
  • 72
  • Highly Influential
  • PDF
Coordinating multi-agent reinforcement learning with limited communication
  • 89
  • Highly Influential
  • PDF
Learning Attentional Communication for Multi-Agent Cooperation
  • 124
  • Highly Influential
  • PDF
Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
  • 48
  • PDF
QueryPOMDP: POMDP-Based Communication in Multiagent Systems
  • 21
  • PDF
Learning to Communicate with Deep Multi-Agent Reinforcement Learning
  • 653
  • Highly Influential
  • PDF
Learning Multiagent Communication with Backpropagation
  • 503
  • PDF
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
  • 1,035
  • PDF
...
1
2
3
4
5
...