Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth
Not on the map. Why?
Abstract (arXiv)
Communication plays a vital role in multi-agent systems, fostering collaboration and coordination. However, in real-world scenarios where communication is bandwidth-limited, existing multi-agent reinforcement learning (MARL) algorithms often provide agents with a binary choice: either transmitting a fixed number of bytes or no information at all. This limitation hinders the ability to effectively utilize the available bandwidth. To overcome this challenge, we present the Dynamic Size Message Scheduling (DSMS) method, which introduces a finer-grained approach to scheduling by considering the actual size of the information to be exchanged. Our contribution lies in adaptively adjusting message sizes using Fourier transform-based compression techniques, enabling agents to tailor their messages to match the allocated bandwidth while striking a balance between information loss and transmission efficiency. Receiving agents can reliably decompress the messages using the inverse Fourier transform. Experimental results demonstrate that DSMS significantly improves performance in multi-agent cooperative tasks by optimizing the utilization of bandwidth and effectively balancing information value.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 63 references that are in the map. First posted on arXiv 16 Jun 2023.
Builds on
27 of 63 references.
References · 27
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
- 2017Counterfactual Multi-Agent Policy Gradientscited by 751
- 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
- 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
- 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
- 2016Learning Multiagent Communication with Backpropagationcited by 366
- 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
- 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
- 2020Learning in the Frequency Domaincited by 198
- 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 175
15 more
- 2022FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecastingcited by 147
- 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 121
- 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 104
- 2019Learning to Schedule Communication in Multi-agent Reinforcement Learningcited by 93
- 2015Spectral Representations for Convolutional Neural Networkscited by 81
- 2019Learning Efficient Multi-agent Communication: An Information Bottleneck Approachcited by 61
- 2020Learning Individually Inferred Communication for Multi-Agent Cooperationcited by 55
- 2019Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Controlcited by 46
- 2023A Survey on Deep Learning based Time Series Analysis with Frequency Transformationcited by 40
- 2019Learning Agent Communication under Limited Bandwidth by Message Pruningcited by 31
- 2020Succinct and Robust Multi-Agent Communication With Temporal Message Controlcited by 29
- 2020Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networkscited by 19
- 2019Improving Coordination in Small-Scale Multi-Agent Deep Reinforcement Learning through Memory-driven Communicationcited by 18
- 2021Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learningcited by 11
- 2020Wireless Feedback Control with Variable Packet Length for Industrial IoTcited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.