{"id":"https://openalex.org/W3168573424","doi":"https://doi.org/10.1145/3447548.3467242","title":"HMRL","display_name":"HMRL","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3168573424","doi":"https://doi.org/10.1145/3447548.3467242","mag":"3168573424"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","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/A5101519280","display_name":"Yun Hua","orcid":"https://orcid.org/0000-0002-1703-9775"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yun Hua","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101927070","display_name":"Xiangfeng Wang","orcid":"https://orcid.org/0000-0003-3064-5128"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangfeng Wang","raw_affiliation_strings":["East China Normal University & Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University & Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101748265","display_name":"Bo Jin","orcid":"https://orcid.org/0000-0003-1028-5989"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Jin","raw_affiliation_strings":["East China Normal University & Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University & Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362638","display_name":"Wenhao Li","orcid":"https://orcid.org/0000-0003-2985-1098"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Li","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087158377","display_name":"Junchi Yan","orcid":"https://orcid.org/0000-0001-9639-7679"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchi Yan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101434435","display_name":"Xiaofeng He","orcid":"https://orcid.org/0000-0002-6911-348X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng He","raw_affiliation_strings":["East China Normal University & Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University & Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046703129","display_name":"Hongyuan Zha","orcid":"https://orcid.org/0000-0001-7493-0911"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyuan Zha","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101519280"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71944686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"637","last_page":"645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9980999827384949,"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/T12676","display_name":"Machine Learning and ELM","score":0.9944000244140625,"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":0.8355414867401123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7715880870819092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557877421379089},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.5546730756759644},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5425390005111694},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.507445752620697},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.48962312936782837},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.475710928440094},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.472662091255188},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.460212379693985},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4426482617855072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1032099723815918},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08274799585342407}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8355414867401123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715880870819092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557877421379089},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.5546730756759644},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5425390005111694},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.507445752620697},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.48962312936782837},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.475710928440094},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.472662091255188},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.460212379693985},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4426482617855072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1032099723815918},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08274799585342407},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447548.3467242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","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":21,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2144794447","https://openalex.org/W2145339207","https://openalex.org/W2151382427","https://openalex.org/W2342662072","https://openalex.org/W2476301537","https://openalex.org/W2581240229","https://openalex.org/W2604763608","https://openalex.org/W2787501667","https://openalex.org/W2790355818","https://openalex.org/W2803767077","https://openalex.org/W2809148419","https://openalex.org/W2918894365","https://openalex.org/W2963176272","https://openalex.org/W2963280855","https://openalex.org/W2963311874","https://openalex.org/W2964118262","https://openalex.org/W2966461828","https://openalex.org/W2970370999","https://openalex.org/W2996148148","https://openalex.org/W3037760466"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W3109396871","https://openalex.org/W2981636907","https://openalex.org/W4384807734"],"abstract_inverted_index":{"In":[0,27],"spite":[1],"of":[2,5,115],"the":[3,53,71,82,95,104,113],"success":[4],"existing":[6],"meta":[7,18,34,55,63,72,76,96,106],"reinforcement":[8,35],"learning":[9,16,36,122],"methods,":[10],"they":[11],"still":[12],"have":[13],"difficulty":[14],"in":[15],"a":[17,32,61,93],"policy":[19,97,121],"effectively":[20,80],"for":[21,41],"RL":[22,44],"problems":[23],"with":[24,49,103,109],"sparse":[25,42,84],"reward.":[26,107],"this":[28],"respect,":[29],"we":[30],"develop":[31],"novel":[33],"framework":[37],"called":[38],"Hyper-Meta":[39],"RL(HMRL),":[40],"reward":[43,77,85],"problems.":[45],"It":[46],"is":[47],"consisted":[48],"three":[50],"modules":[51],"including":[52],"cross-environment":[54],"state":[56,64,73],"embedding":[57],"module":[58],"which":[59,79],"constructs":[60],"common":[62],"space":[65],"to":[66,68],"adapt":[67],"different":[69],"environments;":[70],"based":[74],"environment-specific":[75],"shaping":[78],"extends":[81],"original":[83],"trajectory":[86],"by":[87],"cross-environmental":[88],"knowledge":[89],"complementarity":[90],"and":[91,101,120],"as":[92],"consequence":[94],"achieves":[98],"better":[99],"generalization":[100],"efficiency":[102],"shaped":[105],"Experiments":[108],"sparse-reward":[110],"environments":[111],"show":[112],"superiority":[114],"HMRL":[116],"on":[117],"both":[118],"transferability":[119],"efficiency.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-06-22T00:00:00"}