{"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/gated-attention-architectures-for-task","title":"Gated-Attention Architectures for Task-Oriented Language Grounding","arxiv_id":"1706.07230","date":"2017-06-22","proceeding":null,"authors":["Devendra Singh Chaplot","Kanthashree Mysore Sathyendra","Rama Kumar Pasumarthi","Dheeraj Rajagopal","Ruslan Salakhutdinov"],"abstract":"To perform tasks specified by natural language instructions, autonomous\nagents need to extract semantically meaningful representations of language and\nmap it to visual elements and actions in the environment. This problem is\ncalled task-oriented language grounding. We propose an end-to-end trainable\nneural architecture for task-oriented language grounding in 3D environments\nwhich assumes no prior linguistic or perceptual knowledge and requires only raw\npixels from the environment and the natural language instruction as input. The\nproposed model combines the image and text representations using a\nGated-Attention mechanism and learns a policy to execute the natural language\ninstruction using standard reinforcement and imitation learning methods. We\nshow the effectiveness of the proposed model on unseen instructions as well as\nunseen maps, both quantitatively and qualitatively. We also introduce a novel\nenvironment based on a 3D game engine to simulate the challenges of\ntask-oriented language grounding over a rich set of instructions and\nenvironment states.","url_abs":"http://arxiv.org/abs/1706.07230v2","url_pdf":"http://arxiv.org/pdf/1706.07230v2.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":"gated-attention-architectures-for-task","repo_url":"https://github.com/devendrachaplot/DeepRL-Grounding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.07230","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}