Recent progress in using machine learning models for reasoning tasks has been driven by novel model architectures, large-scale pre-training protocols, and dedicated reasoning datasets for fine-tuning. In this work, to further pursue these advances, we introduce a new data generator for machine reasoning that integrates with an embodied agent. The generated data consists of templated text queries and answers, matched with world-states encoded into a database. The world-states are a result of both world dynamics and the actions of the agent. We show the results of several baseline models on instantiations of train sets. These include pre-trained language models fine-tuned on a text-formatted representation of the database, and graph-structured Transformers operating on a knowledge-graph representation of the database. We find that these models can answer some questions about the world-state, but struggle with others. These results hint at new research directions in designing neural reasoning models and database representations. Code to generate the data will be released at github.com/facebookresearch/neuralmemory

翻译：近期，利用机器学习模型进行推理任务的进展得益于新型模型架构、大规模预训练协议以及专用于微调的推理数据集。为进一步推进这些进展，本研究引入了一个与具身代理集成的机器推理新数据生成器。生成的数据包含模板化的文本查询与答案，并与编码至数据库的世界状态相匹配。世界状态由世界动态与代理行为共同作用产生。我们展示了多个基线模型在训练集实例上的表现，包括在数据库的文本格式化表示上微调的预训练语言模型，以及在数据库的知识图谱表示上运行的图结构Transformer。研究发现，这些模型能够回答部分关于世界状态的问题，但在其他问题上表现欠佳。这些结果揭示了设计神经推理模型与数据库表示的新研究方向。生成数据的代码将在 github.com/facebookresearch/neuralmemory 发布。