Commonsense Knowledge from Scene Graphs for Textual Environments
This addresses the challenge of enhancing reinforcement learning agents in textual environments by leveraging visual commonsense, though it is incremental as it builds on prior knowledge-based approaches.
The paper tackled the problem of imperfect information in text-based games by using commonsense knowledge from visual scene graphs instead of text-based sources, and demonstrated that their methods achieved higher and competitive performance compared to existing state-of-the-art methods.
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 challenge these games, it is effective to complement the missing information by providing knowledge outside the game, such as human common sense. However, such knowledge has only been available from textual information in previous works. In this paper, we investigate the advantage of employing commonsense reasoning obtained from visual datasets such as scene graph datasets. In general, images convey more comprehensive information compared with text for humans. This property enables to extract commonsense relationship knowledge more useful for acting effectively in a game. We compare the statistics of spatial relationships available in Visual Genome (a scene graph dataset) and ConceptNet (a text-based knowledge) to analyze the effectiveness of introducing scene graph datasets. We also conducted experiments on a text-based game task that requires commonsense reasoning. Our experimental results demonstrated that our proposed methods have higher and competitive performance than existing state-of-the-art methods.