{"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/dom-q-net-grounded-rl-on-structured-language","title":"DOM-Q-NET: Grounded RL on Structured Language","arxiv_id":"1902.07257","date":"2019-02-19","proceeding":"ICLR 2019 5","authors":["Sheng Jia","Jamie Kiros","Jimmy Ba"],"abstract":"Building agents to interact with the web would allow for significant\nimprovements in knowledge understanding and representation learning. However,\nweb navigation tasks are difficult for current deep reinforcement learning (RL)\nmodels due to the large discrete action space and the varying number of actions\nbetween the states. In this work, we introduce DOM-Q-NET, a novel architecture\nfor RL-based web navigation to address both of these problems. It parametrizes\nQ functions with separate networks for different action categories: clicking a\nDOM element and typing a string input. Our model utilizes a graph neural\nnetwork to represent the tree-structured HTML of a standard web page. We\ndemonstrate the capabilities of our model on the MiniWoB environment where we\ncan match or outperform existing work without the use of expert demonstrations.\nFurthermore, we show 2x improvements in sample efficiency when training in the\nmulti-task setting, allowing our model to transfer learned behaviours across\ntasks.","url_abs":"http://arxiv.org/abs/1902.07257v1","url_pdf":"http://arxiv.org/pdf/1902.07257v1.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":"dom-q-net-grounded-rl-on-structured-language","repo_url":"https://github.com/Sheng-J/DOM-Q-NET","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":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.07257","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}