Learning Knowledge Graph-based World Models of Textual Environments
World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive narratives, are reinforcement learning environments in which agents perceive and interact with the world using textual natural language. These environments contain long, multi-step puzzles or quests woven through a world that is filled with hundreds of characters, locations, and objects. Our world model learns to simultaneously: (1) predict changes in the world caused by an agent's actions when representing the world as a knowledge graph; and (2) generate the set of contextually relevant natural language actions required to operate in the world. We frame this task as a Set of Sequences generation problem by exploiting the inherent structure of knowledge graphs and actions and introduce both a transformer-based multi-task architecture and a loss function to train it. A zero-shot ablation study on never-before-seen textual worlds shows that our methodology significantly outperforms existing textual world modeling techniques as well as the importance of each of our contributions.
Code (0)
등록된 구현이 없습니다.
Tasks
Action ParsingKnowledge Graphstext-based gamesSimilar Papers 제목 키워드 기반
Commonsense Knowledge from Scene Graphs for Textual Environments
Text-based games are becoming commonly used in reinforcement learning as real-world simulation environments. They are usually imperfect information games, and their interactions are only in the textual modality. To chall…
Common Sense Reasoningtext-based gamesA Systematic Survey of Text Worlds as Embodied Natural Language Environments
Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D environments, are rendered exclusively using textual descriptions. These environments offer an alternative to higher-fidelity 3D environments…
Common Sense ReasoningKnowledge GraphsTransfer LearningA Systematic Survey of Text Worlds as Embodied Natural Language Environments
Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D environments, are rendered exclusively using textual descriptions. These environments offer an alternative to higher-fidelity 3D environments…
Common Sense ReasoningKnowledge GraphsTransfer LearningJust KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes
Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framewo…
Knowledge DistillationKnowledge GraphsContext-driven Visual Object Recognition based on Knowledge Graphs
Current deep learning methods for object recognition are purely data-driven and require a large number of training samples to achieve good results. Due to their sole dependence on image data, these methods tend to fail w…
Knowledge GraphsObjectObject RecognitionTransfer Learning