On The Pitfalls Of Measuring Emergent Communication

Abstract

How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to an increase in reward or task success. This is a useful indicator, but provides only a coarse measure of the agent's learned communication abilities. As we move towards more complex environments, it becomes imperative to have a set of finer tools that allow qualitative and quantitative insights into the emergence of communication. This may be especially useful to allow humans to monitor agents' behaviour, whether for fault detection, assessing performance, or even building trust. In this paper, we examine a few intuitive existing metrics for measuring communication, and show that they can be misleading. Specifically, by training deep reinforcement learning agents to play simple matrix games augmented with a communication channel, we find a scenario where agents appear to communicate (their messages provide in

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keylowe2019on

Related papers

• On The Role Of Emergent Communication For Social Learning In Multi-agent Reinforcement Learning (2023)0.00
• Multi-agent Curricula And Emergent Implicit Signaling (2021)0.00
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Inductive Bias For Emergent Communication In A Continuous Setting (2023)0.00
• Mimicry And The Emergence Of Cooperative Communication (2024)0.00
• Low-bandwidth Communication Emerges Naturally In Multi-agent Learning Systems (2020)0.00
• Effective Communications: A Joint Learning And Communication Framework For Multi-agent Reinforcement Learning Over Noisy Channels (2021)0.00
• Over-communicate No More: Situated RL Agents Learn Concise Communication Protocols (2022)0.00