GDL and DDL of emergent languages.

In language emergence, neural agents acquire communication skills by interacting with one another and the environment. Through these interactions, agents learn to connect or ground their observations to the messages they utter, forming a shared consensus about the meaning of the messages. Such connections form what we refer to as a grounding map. However, these maps can often be complicated, unstructured, and contain redundant connections. In this paper, we introduce two novel functional pressures, modeled as differentiable auxiliary losses, to simplify and structure the grounding maps. The first pressure enforces compositionality via topological similarity, which has been previously discussed but has not been modeled or utilized as a differentiable auxiliary loss. The second functional pressure, which is conceptually novel, imposes sparsity in the grounding map by pruning weaker connections while strengthening the stronger ones. We conduct experiments in multiple value-attribute environments with varying communication channels. Our methods achieve improved out-of-domain regularization and rapid convergence over baseline approaches. Furthermore, introduced functional pressures are robust to the changes in experimental conditions and able to operate with minimum training data. We note that functional pressures cause simpler and more structured emergent languages showing distinct characteristics depending on the functional pressure employed. Enhancing grounding map sparsity yields the best performance and the languages with the most compressible grammar. In summary, our novel functional pressures, focusing on compositionality and sparse groundings, expedite the development of simpler, more structured languages while enhancing their generalization capabilities. Exploring alternative types of functional pressures and combining them in agent training may be beneficial in the ongoing quest for improved emergent languages.在语言涌现（language emergence）研究领域中，神经AI智能体（neural agents）通过彼此交互以及与环境的交互来习得沟通技能。通过此类交互，智能体得以学习将自身的观测结果与所发出的话语建立关联并完成接地，进而就这些话语的含义形成共享共识。此类关联便构成了我们所称的接地映射（grounding map）。然而此类映射往往结构复杂、缺乏规整性，且包含冗余关联。本文提出两种全新的功能压力（functional pressures），将其建模为可微辅助损失函数（differentiable auxiliary losses），用于简化并规整接地映射。第一种功能压力通过拓扑相似性来强化组合性（compositionality），该概念此前虽已有讨论，但尚未被建模为可微辅助损失函数并加以利用。第二种功能压力则在概念上具有创新性，它通过剪去较弱的关联、强化较强的关联，来实现接地映射的稀疏性（sparsity）约束。我们在多种具备不同沟通通道的价值-属性环境中开展了实验。相较于基线方法（baseline approaches），我们的方法实现了更优的域外（out-of-domain）正则化效果与更快的收敛速度。此外，所提出的功能压力对实验条件的变化具备鲁棒性，且仅需少量训练数据即可生效。我们注意到，不同的功能压力会催生结构更简洁、更规整的涌现语言，且这些语言会依据所采用的功能压力展现出各异的特性。强化接地映射的稀疏性能够获得最优的实验性能，且其所催生的语言拥有最具可压缩性的语法结构。综上，我们所提出的聚焦于组合性与稀疏接地的新型功能压力，不仅加速了更简洁、更具规整性的语言的涌现，同时还提升了这些语言的泛化能力（generalization capabilities）。在当前对更优质涌现语言的探索中，探索其他类型的功能压力并将其应用于智能体训练中，或将带来可观的收益。