{"id":"https://openalex.org/W7133239784","doi":"https://doi.org/10.52202/075280-0973","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","display_name":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7133239784","doi":"https://doi.org/10.52202/075280-0973"},"language":"en","primary_location":{"id":"doi:10.52202/075280-0973","doi":"https://doi.org/10.52202/075280-0973","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-0973","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.18258","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127805663","display_name":"Zhihan Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127780764","display_name":"Miao Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127803424","display_name":"Wei Xiong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146675374","display_name":"Han Zhong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127858363","display_name":"Hao Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024816616","display_name":"Shenao Zhang","orcid":"https://orcid.org/0009-0006-5083-606X","observed_orcids":["https://orcid.org/0009-0006-5083-606X","https://orcid.org/0009-0008-2501-8967","https://orcid.org/0009-0004-5233-3373"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shenao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127868529","display_name":"Sirui Zheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sirui Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127866215","display_name":"Zhuoran Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuoran Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5146708871","display_name":"Zhaoran Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoran Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3541,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60237131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"22151","last_page":"22165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7250999808311462,"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":0.7250999808311462,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.08950000256299973,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.029200000688433647,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.4869999885559082},{"id":"https://openalex.org/keywords/estimation","display_name":"estimation","score":0.5080000162124634},{"id":"https://openalex.org/keywords/planning","display_name":"planning","score":0.9169999957084656},{"id":"https://openalex.org/keywords/objective-function","display_name":"objective function","score":0.5339999794960022},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.7149999737739563},{"id":"https://openalex.org/keywords/robotic-exploration","display_name":"robot exploration","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5347999930381775},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40369999408721924},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2531000077724457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2476000040769577},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2467000037431717},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2425999939441681}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/075280-0973","doi":"https://doi.org/10.52202/075280-0973","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-0973","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.18258","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.18258","pdf_url":"https://arxiv.org/pdf/2305.18258","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.18258","doi":"https://doi.org/10.48550/arxiv.2305.18258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.18258","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.18258","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.18258","pdf_url":"https://arxiv.org/pdf/2305.18258","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133239784.pdf","grobid_xml":"https://content.openalex.org/works/W7133239784.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4300980646","https://openalex.org/W3211416934","https://openalex.org/W3040712623","https://openalex.org/W7100193261","https://openalex.org/W7099603424","https://openalex.org/W7111034818","https://openalex.org/W3170402103","https://openalex.org/W6926936692","https://openalex.org/W6959643065","https://openalex.org/W3004977066"],"abstract_inverted_index":{"In":[0],"online":[1,26,169],"reinforcement":[2],"learning":[3],"(online":[4],"RL),":[5],"balancing":[6,99],"exploration":[7,100],"and":[8,36,95,101,122,147,187],"exploitation":[9,102],"is":[10,123,188],"crucial":[11],"for":[12,117],"finding":[13],"an":[14,73],"optimal":[15],"policy":[16],"in":[17,39,144,158],"a":[18,88,110,155,183],"sample-efficient":[19,25,168],"way.":[20],"To":[21,67],"achieve":[22],"this,":[23],"existing":[24,167],"RL":[27,75,136,170,194],"algorithms":[28,171],"typically":[29],"consist":[30],"of":[31,48,142],"three":[32],"components:":[33],"estimation,":[34],"planning,":[35],"exploration.":[37],"However,":[38],"order":[40],"to":[41,54,79,85,126,138],"cope":[42],"with":[43,113,162,166,172,191],"general":[44,114,173],"function":[45,115,174],"approximators,":[46],"most":[47],"them":[49],"involve":[50],"impractical":[51],"algorithmic":[52],"components":[53,97],"incentivize":[55],"exploration,":[56],"such":[57],"as":[58],"optimization":[59],"within":[60],"data-dependent":[61],"level-sets":[62],"or":[63],"complicated":[64],"sampling":[65],"procedures.":[66],"address":[68],"this":[69],"challenge,":[70],"we":[71,105,133],"propose":[72],"easy-to-implement":[74],"framework":[76],"called":[77],"\\textit{Maximize":[78],"Explore}":[80],"(\\texttt{MEX}),":[81],"which":[82,150],"only":[83],"needs":[84],"optimize":[86],"\\emph{unconstrainedly}":[87],"single":[89],"objective":[90],"that":[91,107],"integrates":[92],"the":[93],"estimation":[94],"planning":[96],"while":[98,181],"automatically.":[103],"Theoretically,":[104],"prove":[106],"\\texttt{MEX}":[108,176],"achieves":[109,177],"sublinear":[111],"regret":[112],"approximations":[116],"Markov":[118,129],"decision":[119],"processes":[120],"(MDP)":[121],"further":[124],"extendable":[125],"two-player":[127],"zero-sum":[128],"games":[130],"(MG).":[131],"Meanwhile,":[132],"adapt":[134],"deep":[135,193],"baselines":[137,153],"design":[139],"practical":[140],"versions":[141],"\\texttt{MEX},":[143],"both":[145],"model-free":[146],"model-based":[148],"manners,":[149],"can":[151],"outperform":[152],"by":[154],"stable":[156],"margin":[157],"various":[159],"MuJoCo":[160],"environments":[161],"sparse":[163],"rewards.":[164],"Compared":[165],"approximations,":[175],"similar":[178],"sample":[179],"efficiency":[180],"enjoying":[182],"lower":[184],"computational":[185],"cost":[186],"more":[189],"compatible":[190],"modern":[192],"methods.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-03-03T00:00:00"}