{"id":"https://openalex.org/W2964241178","doi":"https://doi.org/10.24963/ijcai.2018/626","title":"Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents","display_name":"Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2964241178","doi":"https://doi.org/10.24963/ijcai.2018/626","mag":"2964241178"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/626","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/626","pdf_url":"https://www.ijcai.org/proceedings/2018/0626.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0626.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110635444","display_name":"Wenhan Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenhan Xiong","raw_affiliation_strings":["University of California, Santa Barbara"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051951021","display_name":"Xiaoxiao Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxiao Guo","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101583277","display_name":"Mo Yu","orcid":"https://orcid.org/0000-0003-0949-6113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mo Yu","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112248869","display_name":"Shiyu Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Chang","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808331","display_name":"Bowen Zhou","orcid":"https://orcid.org/0000-0003-1062-9526"},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Zhou","raw_affiliation_strings":["JD AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD AI Research","institution_ids":["https://openalex.org/I72427458"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702485","display_name":"William Yang Wang","orcid":"https://orcid.org/0000-0001-6153-8240"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Yang Wang","raw_affiliation_strings":["University of California, Santa Barbara"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100702485"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4503","last_page":"4509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8584835529327393},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7806164622306824},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6479311585426331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5882898569107056},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.544420599937439},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.533659040927887},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5005054473876953},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.48689189553260803},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47721177339553833},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.43931037187576294},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4234582781791687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8584835529327393},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7806164622306824},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6479311585426331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5882898569107056},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.544420599937439},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.533659040927887},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5005054473876953},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48689189553260803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47721177339553833},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.43931037187576294},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4234582781791687},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/626","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/626","pdf_url":"https://www.ijcai.org/proceedings/2018/0626.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/626","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/626","pdf_url":"https://www.ijcai.org/proceedings/2018/0626.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964241178.pdf","grobid_xml":"https://content.openalex.org/works/W2964241178.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1522301498","https://openalex.org/W1602500555","https://openalex.org/W1931877416","https://openalex.org/W1933065844","https://openalex.org/W2005814556","https://openalex.org/W2051228319","https://openalex.org/W2097900976","https://openalex.org/W2118781169","https://openalex.org/W2119717200","https://openalex.org/W2122223050","https://openalex.org/W2138455848","https://openalex.org/W2145339207","https://openalex.org/W2236233024","https://openalex.org/W2467589492","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2950632879","https://openalex.org/W2962736495","https://openalex.org/W2963367210","https://openalex.org/W4242421948"],"related_works":["https://openalex.org/W4288263119","https://openalex.org/W3015724364","https://openalex.org/W2967994095","https://openalex.org/W4285240985","https://openalex.org/W2900126711","https://openalex.org/W4286930972","https://openalex.org/W3202115945","https://openalex.org/W2542958340","https://openalex.org/W4389520438","https://openalex.org/W1991374750"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,38,73,84,96,109],"task":[3],"of":[4,99,111],"learning":[5,26,34,53],"to":[6,36,69],"interpret":[7],"natural":[8],"language":[9,18],"instructions":[10],"by":[11,87],"jointly":[12],"reasoning":[13],"with":[14,25],"visual":[15],"observations":[16],"and":[17,30,54,63],"inputs.":[19],"Unlike":[20],"current":[21],"methods":[22],"which":[23,48],"start":[24],"from":[27],"demonstrations":[28],"(LfD)":[29],"then":[31],"use":[32],"reinforcement":[33],"(RL)":[35],"fine-tune":[37],"model":[39,76],"parameters,":[40],"we":[41],"propose":[42],"a":[43,90],"novel":[44],"policy":[45,112],"optimization":[46],"algorithm":[47],"can":[49],"dynamically":[50],"schedule":[51],"demonstration":[52],"RL.":[55],"The":[56],"proposed":[57,80],"training":[58],"paradigm":[59],"provides":[60],"efficient":[61],"exploration":[62,97],"generalization":[64],"beyond":[65],"existing":[66,70],"methods.":[67],"Comparing":[68],"ensemble":[71],"models,":[72],"best":[74],"single":[75],"based":[77],"on":[78,89,108],"our":[79,100,103],"method":[81],"tremendously":[82],"decreases":[83],"execution":[85],"error":[86],"55%":[88],"block-world":[91],"environment.":[92],"To":[93],"further":[94],"illustrate":[95],"strategy":[98],"RL":[101],"algorithm,":[102],"paper":[104],"includes":[105],"systematic":[106],"studies":[107],"evolution":[110],"entropy":[113],"during":[114],"training.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}