{"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/playing-text-adventure-games-with-graph-based","title":"Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning","arxiv_id":"1812.01628","date":"2018-12-04","proceeding":"NAACL 2019 6","authors":["Prithviraj Ammanabrolu","Mark O. Riedl"],"abstract":"Text-based adventure games provide a platform on which to explore\nreinforcement learning in the context of a combinatorial action space, such as\nnatural language. We present a deep reinforcement learning architecture that\nrepresents the game state as a knowledge graph which is learned during\nexploration. This graph is used to prune the action space, enabling more\nefficient exploration. The question of which action to take can be reduced to a\nquestion-answering task, a form of transfer learning that pre-trains certain\nparts of our architecture. In experiments using the TextWorld framework, we\nshow that our proposed technique can learn a control policy faster than\nbaseline alternatives. We have also open-sourced our code at\nhttps://github.com/rajammanabrolu/KG-DQN.","url_abs":"http://arxiv.org/abs/1812.01628v2","url_pdf":"http://arxiv.org/pdf/1812.01628v2.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":[{"paper_slug":"playing-text-adventure-games-with-graph-based","repo_url":"https://github.com/rajammanabrolu/KG-DQN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.01628","atlas_url":"https://app.syntology.ai/?focus=1812.01628","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}