To build agents that can collaborate effectively with others, recent research has trained artificial agents to communicate with each other in Lewis-style referential games. However, this often leads to successful but uninterpretable communication. We argue that this is due to the game objective: communicating about a single object in a shared visual context is prone to overfitting and does not encourage language useful beyond concrete reference. In contrast, human language conveys a rich variety of abstract ideas. To promote such skills, we propose games that require communicating generalizations over sets of objects representing abstract visual concepts, optionally with separate contexts for each agent. We find that these games greatly improve systematicity and interpretability of the learned languages, according to several metrics in the literature. Finally, we propose a method for identifying logical operations embedded in the emergent languages by learning an approximate compositional reconstruction of the language.
翻译:为了建立能够与他人有效合作的代理机构,最近的研究培训了人工代理机构,使其在刘易斯式优惠游戏中相互沟通。然而,这往往导致成功但无法解释的沟通。我们争辩说,这是因为游戏的目的:在共同视觉背景下就单一对象进行沟通容易过度适应,而且不会鼓励除具体参考外有用的语言。相反,人文传达了丰富的抽象思想。为了推广这种技能,我们建议游戏,要求对代表抽象视觉概念的成套物体进行通俗交流,每个代理机构可选择不同的环境。我们发现,根据文献中的若干衡量标准,这些游戏极大地改进了所学语言的系统性和可解释性。最后,我们建议了一种方法,通过学习语言的大致构成重建,确定新语言中包含的逻辑操作。