{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-knowledge-graph-based-world-models","title":"Learning Knowledge Graph-based World Models of Textual Environments","arxiv_id":"2106.09608","date":"2021-06-17","proceeding":"NeurIPS 2021 12","authors":["Prithviraj Ammanabrolu","Mark O. Riedl"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2106.09608v2","url_pdf":"https://arxiv.org/pdf/2106.09608v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"action-parsing","task_name":"Action Parsing"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"text-based-games","task_name":"text-based games"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-parsing-on-jerichoworld","task":"Action Parsing","dataset":"JerichoWorld","model":"Worldformer","rank_in_archive_order":1,"of":3,"metrics":{"Set accuracy":"23.22"},"uses_additional_data":false},{"leaderboard":"/sota/action-parsing-on-jerichoworld","task":"Action Parsing","dataset":"JerichoWorld","model":"CALM","rank_in_archive_order":3,"of":3,"metrics":{"Set accuracy":"13.79"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-graphs-on-jerichoworld","task":"Knowledge Graphs","dataset":"JerichoWorld","model":"Worldformer","rank_in_archive_order":1,"of":5,"metrics":{"Set accuracy":"39.15"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-graphs-on-jerichoworld","task":"Knowledge Graphs","dataset":"JerichoWorld","model":"GATA-W","rank_in_archive_order":3,"of":5,"metrics":{"Set accuracy":"24.06"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.09608","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}