يوفر التعلم العميق التعلم نهجا واعدا للألعاب القائمة على النصوص في دراسة التواصل الطبيعي باللغة الطبيعية بين البشر والوكلاء الاصطناعي.ومع ذلك، لا يزال التعميم يمثل تحديا كبيرا حيث يعتمد الوكلاء بشكل خطير على تعقيد ومجموعة متنوعة من المهام التدريبية.في هذه الورقة، نتعلم هذه المشكلة عن طريق إدخال إطار هرمي مبني على وكيل RL المعلق الرسم البياني المعلق.في المستوى العالي، يتم تنفيذ سياسة META لتحلل اللعبة بأكملها في مجموعة من المهام الفرعية المحددة بواسطة أهداف نصية، وحدد أحدها بناء على KG.ثم يتم تنفيذ سياسة فرعية في المستوى المنخفض لإجراء تعلم التعزيز المكيف للأهداف.نقوم بإجراء تجارب على الألعاب ذات مستويات صعوبة مختلفة وإظهار أن الطريقة المقترحة تتمتع بالتعميمات المواتية.
Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents. However, the generalization still remains a big challenge as the agents depend critically on the complexity and variety of training tasks. In this paper, we address this problem by introducing a hierarchical framework built upon the knowledge graph-based RL agent. In the high level, a meta-policy is executed to decompose the whole game into a set of subtasks specified by textual goals, and select one of them based on the KG. Then a sub-policy in the low level is executed to conduct goal-conditioned reinforcement learning. We carry out experiments on games with various difficulty levels and show that the proposed method enjoys favorable generalizability.
References used
https://aclanthology.org/
Text-based games can be used to develop task-oriented text agents for accomplishing tasks with high-level language instructions, which has potential applications in domains such as human-robot interaction. Given a text instruction, reinforcement lear
The current state-of-the-art model HiAGM for hierarchical text classification has two limitations. First, it correlates each text sample with all labels in the dataset which contains irrelevant information. Second, it does not consider any statistica
Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural networ
Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen components. Motivated by trad
We consider the hierarchical representation of documents as graphs and use geometric deep learning to classify them into different categories. While graph neural networks can efficiently handle the variable structure of hierarchical documents using t