The literature in modern machine learning has only negative results for learning to communicate between competitive agents using standard RL. We introduce a modified sender-receiver game to study the spectrum of partially-competitive scenarios and show communication can indeed emerge in a competitive setting. We empirically demonstrate three key takeaways for future research. First, we show that communication is proportional to cooperation, and it can occur for partially competitive scenarios using standard learning algorithms. Second, we highlight the difference between communication and manipulation and extend previous metrics of communication to the competitive case. Third, we investigate the negotiation game where previous work failed to learn communication between independent agents (Cao et al., 2018). We show that, in this setting, both agents must benefit from communication for it to emerge; and, with a slight modification to the game, we demonstrate successful communication between competitive agents. We hope this work overturns misconceptions and inspires more research in competitive emergent communication.

在现代机器学习中，标准强化学习算法在学习竞争代理之间的通信方面表现出仅有的负面结果。我们引入了一种改进的发送者-接收者游戏来研究部分竞争场景的光谱，并展示了通信确实可以在竞争环境中出现。我们通过实验证明了以下三个关键的研究成果。首先，我们表明通信与合作成正比例，并且可以使用标准学习算法在部分竞争的场景中发生。其次，我们强调了通信和操纵之间的区别，并将以前的通信度量扩展到了竞争的情况下。第三，我们研究了协商游戏，在此之前的研究未能学习到独立代理之间的通信（Cao et al.，2018）。我们证明，在这种情况下，两个代理都必须受益于通信才能出现；通过对游戏进行轻微修改，我们展示了竞争代理之间成功通信的情况。我们希望这项工作能推翻误解并激发更多的竞争性新兴通信方面的研究。

竞争中的紧急沟通