{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/scheduled-policy-optimization-for-natural","title":"Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents","arxiv_id":"1806.06187","date":"2018-06-16","proceeding":null,"authors":["Wenhan Xiong","Xiaoxiao Guo","Mo Yu","Shiyu Chang","Bo-Wen Zhou","William Yang Wang"],"abstract":"We investigate the task of learning to follow natural language instructions\nby jointly reasoning with visual observations and language inputs. In contrast\nto existing methods which start with learning from demonstrations (LfD) and\nthen use reinforcement learning (RL) to fine-tune the model parameters, we\npropose a novel policy optimization algorithm which dynamically schedules\ndemonstration learning and RL. The proposed training paradigm provides\nefficient exploration and better generalization beyond existing methods.\nComparing to existing ensemble models, the best single model based on our\nproposed method tremendously decreases the execution error by over 50% on a\nblock-world environment. To further illustrate the exploration strategy of our\nRL algorithm, We also include systematic studies on the evolution of policy\nentropy during training.","url_abs":"http://arxiv.org/abs/1806.06187v2","url_pdf":"http://arxiv.org/pdf/1806.06187v2.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":"scheduled-policy-optimization-for-natural","repo_url":"https://github.com/xwhan/walk_the_blocks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"scheduled-policy-optimization-for-natural","repo_url":"https://github.com/clic-lab/ciff","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"scheduled-policy-optimization-for-natural","repo_url":"https://github.com/lil-lab/ciff","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"xwhan/walk_the_blocks","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"clic-lab/ciff","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lil-lab/ciff","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a3311c629719ded5ef04b03ab922190c25153e38858cf7bd5f53e27f6f60ccee","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}