Low-bandwidth Communication Emerges Naturally In Multi-agent Learning Systems

Abstract

In this work, we study emergent communication through the lens of cooperative multi-agent behavior in nature. Using insights from animal communication, we propose a spectrum from low-bandwidth (e.g. pheromone trails) to high-bandwidth (e.g. compositional language) communication that is based on the cognitive, perceptual, and behavioral capabilities of social agents. Through a series of experiments with pursuit-evasion games, we identify multi-agent reinforcement learning algorithms as a computational model for the low-bandwidth end of the communication spectrum.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygrupen2020low

Related papers

• Multi-agent Curricula And Emergent Implicit Signaling (2021)0.00
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Mimicry And The Emergence Of Cooperative Communication (2024)0.00
• On The Role Of Emergent Communication For Social Learning In Multi-agent Reinforcement Learning (2023)0.00
• Cooperative Multi-agent Reinforcement Learning For Low-level Wireless Communication (2018)0.00
• Learning Emergent Discrete Message Communication For Cooperative Reinforcement Learning (2021)5.24
• Learning When To Communicate At Scale In Multiagent Cooperative And Competitive Tasks (2018)0.00
• Counterfactual Multi-agent Reinforcement Learning With Graph Convolution Communication (2020)0.00