{"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/situated-mapping-of-sequential-instructions","title":"Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation","arxiv_id":"1805.10209","date":"2018-05-25","proceeding":"ACL 2018 7","authors":["Alane Suhr","Yoav Artzi"],"abstract":"We propose a learning approach for mapping context-dependent sequential\ninstructions to actions. We address the problem of discourse and state\ndependencies with an attention-based model that considers both the history of\nthe interaction and the state of the world. To train from start and goal states\nwithout access to demonstrations, we propose SESTRA, a learning algorithm that\ntakes advantage of single-step reward observations and immediate expected\nreward maximization. We evaluate on the SCONE domains, and show absolute\naccuracy improvements of 9.8%-25.3% across the domains over approaches that use\nhigh-level logical representations.","url_abs":"http://arxiv.org/abs/1805.10209v2","url_pdf":"http://arxiv.org/pdf/1805.10209v2.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":"situated-mapping-of-sequential-instructions","repo_url":"https://github.com/clic-lab/scone","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.10209","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}