{"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/representation-learning-for-grounded-spatial","title":"Representation Learning for Grounded Spatial Reasoning","arxiv_id":"1707.03938","date":"2017-07-13","proceeding":"TACL 2018 1","authors":["Michael Janner","Karthik Narasimhan","Regina Barzilay"],"abstract":"The interpretation of spatial references is highly contextual, requiring\njoint inference over both language and the environment. We consider the task of\nspatial reasoning in a simulated environment, where an agent can act and\nreceive rewards. The proposed model learns a representation of the world\nsteered by instruction text. This design allows for precise alignment of local\nneighborhoods with corresponding verbalizations, while also handling global\nreferences in the instructions. We train our model with reinforcement learning\nusing a variant of generalized value iteration. The model outperforms\nstate-of-the-art approaches on several metrics, yielding a 45% reduction in\ngoal localization error.","url_abs":"http://arxiv.org/abs/1707.03938v2","url_pdf":"http://arxiv.org/pdf/1707.03938v2.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":"representation-learning-for-grounded-spatial","repo_url":"https://github.com/JannerM/spatial-reasoning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"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"},{"task_slug":"spatial-reasoning","task_name":"Spatial Reasoning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.03938","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}