论文标题
本质上动机的作曲语言出现
Intrinsically Motivated Compositional Language Emergence
论文作者
论文摘要
最近，关于在模拟环境中相互作用的人造代理的紧急沟通中进行了大量研究。最近的研究表明，通常，新兴语言不遵循自然语言的组成模式。为了解决这个问题，现有作品提出了有限的渠道容量，作为学习高度构图语言的重要限制。在本文中，我们表明这不是足够的条件，并提出了一个内在的奖励框架，以改善紧急交流中的组成性。我们使用两个代理使用强化学习设置-A \ textIt {task-ware}扬声器和\ textit {state-ware}侦听器，这些听众是进行通信以执行一组任务所需的。通过我们对三种不同的参考游戏设置的实验，包括新颖的环境GCOMM，我们显示了内在的奖励提高了组合性分数，$ \ of of $ \ mathbf {1.5-2} $乘以使用有限通道容量的现有框架的$倍。
Recently, there has been a great deal of research in emergent communication on artificial agents interacting in simulated environments. Recent studies have revealed that, in general, emergent languages do not follow the compositionality patterns of natural language. To deal with this, existing works have proposed a limited channel capacity as an important constraint for learning highly compositional languages. In this paper, we show that this is not a sufficient condition and propose an intrinsic reward framework for improving compositionality in emergent communication. We use a reinforcement learning setting with two agents -- a \textit{task-aware} Speaker and a \textit{state-aware} Listener that are required to communicate to perform a set of tasks. Through our experiments on three different referential game setups, including a novel environment gComm, we show intrinsic rewards improve compositionality scores by $\approx \mathbf{1.5-2}$ times that of existing frameworks that use limited channel capacity.
