{"id":"https://openalex.org/W4392824421","doi":"https://doi.org/10.1145/3638584.3638661","title":"Improve the efficiency of deep reinforcement learning through semantic exploration guided by natural language","display_name":"Improve the efficiency of deep reinforcement learning through semantic exploration guided by natural language","publication_year":2023,"publication_date":"2023-12-08","ids":{"openalex":"https://openalex.org/W4392824421","doi":"https://doi.org/10.1145/3638584.3638661"},"language":"en","primary_location":{"id":"doi:10.1145/3638584.3638661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638584.3638661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091351643","display_name":"Zhourui Guo","orcid":"https://orcid.org/0009-0002-3416-7848"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhourui Guo","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, China and Institute of Automation,Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0009-0002-3416-7848","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China and Institute of Automation,Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066580963","display_name":"Yao Meng","orcid":"https://orcid.org/0000-0001-8782-5918"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yao","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-8782-5918","affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022535706","display_name":"Yang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, China and Institute of Automation,Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-2711-7746","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China and Institute of Automation,Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083652259","display_name":"Qiyue Yin","orcid":"https://orcid.org/0000-0002-3442-6275"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyue Yin","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, China and Institute of Automation,Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-3442-6275","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China and Institute of Automation,Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091351643"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20392316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9941999912261963,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.784320592880249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512168884277344},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6100993752479553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48595869541168213},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.46131348609924316},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4606509208679199},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33342480659484863},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05550304055213928}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.784320592880249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512168884277344},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6100993752479553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48595869541168213},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.46131348609924316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4606509208679199},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33342480659484863},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05550304055213928},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3638584.3638661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638584.3638661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2561715562","https://openalex.org/W2902729397","https://openalex.org/W3007295596","https://openalex.org/W3134840027","https://openalex.org/W3175599258","https://openalex.org/W3197318324","https://openalex.org/W3208960289","https://openalex.org/W3214506775","https://openalex.org/W4223605818","https://openalex.org/W4225963367","https://openalex.org/W4283332982","https://openalex.org/W4286892033","https://openalex.org/W4287278739","https://openalex.org/W6773377091"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W2894473080","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,7,46],"is":[2,48,115],"a":[3,16,71,80,89,95,105,116,125,191,209],"powerful":[4],"technique":[5],"for":[6,74,83],"from":[8,145],"trial":[9],"and":[10,64,91,110,112,136,139,155],"error,":[11],"but":[12],"it":[13,207],"often":[14],"requires":[15],"large":[17,117],"number":[18,185],"of":[19,50,107,119,133,180,186,194],"interactions":[20,121,187],"to":[21,41,128,148,189,197],"achieve":[22],"good":[23],"performance.":[24],"In":[25],"some":[26],"domains,":[27],"such":[28],"as":[29,104],"sparse-reward":[30],"tasks,":[31],"an":[32,169],"oracle":[33,56,66,87,204],"that":[34,113,199],"can":[35,101,175],"provide":[36],"useful":[37],"feedback":[38],"or":[39,62,205],"guidance":[40],"the":[42,45,55,65,86,99,130,134,137,141,146,150,161,178,184,203],"agent":[43,135],"during":[44],"process":[47],"really":[49],"great":[51],"importance.":[52],"However,":[53],"querying":[54],"too":[57],"frequently":[58],"may":[59,67],"be":[60,102],"costly":[61],"impractical,":[63],"not":[68,201],"always":[69],"have":[70],"clear":[72],"answer":[73],"every":[75],"situation.":[76],"Therefore,":[77],"we":[78],"propose":[79],"novel":[81],"method":[82,167,174],"interacting":[84],"with":[85],"in":[88,208],"selective":[90],"efficient":[92],"way,":[93],"using":[94],"retrieval-based":[96],"approach.":[97],"Since":[98],"interaction":[100],"modeled":[103],"sequence":[106],"templated":[108],"questions":[109],"answers,":[111],"there":[114],"corpus":[118,147],"previous":[120],"available.":[122],"We":[123,164],"use":[124,202,206],"neural":[126],"network":[127],"encode":[129],"current":[131],"state":[132],"oracle,":[138],"retrieve":[140],"most":[142],"relevant":[143],"question":[144],"ask":[149],"oracle.":[151],"The":[152],"agent\u2019s":[153],"policy":[154],"value":[156],"function":[157],"was":[158],"updated":[159],"by":[160,182],"oracle\u2019s":[162],"answer.":[163],"evaluate":[165],"our":[166],"on":[168],"object":[170],"manipulation":[171],"task.":[172],"Our":[173],"significantly":[176],"improve":[177],"efficiency":[179],"RL":[181],"reducing":[183],"needed":[188],"reach":[190],"certain":[192],"level":[193],"performance,":[195],"compared":[196],"baselines":[198],"do":[200],"naive":[210],"way.":[211]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}