{"id":"https://openalex.org/W4281697451","doi":"https://doi.org/10.48550/arxiv.2206.00316","title":"Model Generation with Provable Coverability for Offline Reinforcement Learning","display_name":"Model Generation with Provable Coverability for Offline Reinforcement Learning","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4281697451","doi":"https://doi.org/10.48550/arxiv.2206.00316"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.00316","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.00316","pdf_url":"https://arxiv.org/pdf/2206.00316","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.00316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037623663","display_name":"Chengxing Jia","orcid":"https://orcid.org/0009-0000-3421-606X","observed_orcids":["https://orcid.org/0009-0000-3421-606X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Chengxing","raw_affiliation_strings":["National Key Laboratory of Novel Software Technology , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Novel Software Technology , Nanjing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010649438","display_name":"Hao Yin","orcid":"https://orcid.org/0000-0003-0258-1403","observed_orcids":["https://orcid.org/0000-0003-0258-1403","https://orcid.org/0009-0006-8512-3879","https://orcid.org/0000-0003-4076-7065"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Hao","raw_affiliation_strings":["National Key Laboratory of Novel Software Technology , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Novel Software Technology , Nanjing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074785691","display_name":"Chenxiao Gao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Chenxiao","raw_affiliation_strings":["National Key Laboratory of Novel Software Technology , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Novel Software Technology , Nanjing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076801826","display_name":"Xu Tian","orcid":"https://orcid.org/0000-0001-5824-7020","observed_orcids":["https://orcid.org/0000-0001-5824-7020","https://orcid.org/0000-0001-9409-448X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Tian","raw_affiliation_strings":["National Key Laboratory of Novel Software Technology , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Novel Software Technology , Nanjing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390943","display_name":"Lei Yuan","orcid":"https://orcid.org/0000-0003-3714-5177","observed_orcids":["https://orcid.org/0000-0003-3714-5177","https://orcid.org/0009-0002-9750-3992"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Lei","raw_affiliation_strings":["National Key Laboratory of Novel Software Technology , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Novel Software Technology , Nanjing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035138959","display_name":"Zongzhang Zhang","orcid":"https://orcid.org/0000-0002-9238-4747","observed_orcids":["https://orcid.org/0000-0002-9238-4747"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zongzhang","raw_affiliation_strings":["National Key Laboratory of Novel Software Technology , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Novel Software Technology , Nanjing , China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458530","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-8209-2898","observed_orcids":["https://orcid.org/0000-0002-8209-2898"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yang","raw_affiliation_strings":["National Key Laboratory of Novel Software Technology , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Novel Software Technology , Nanjing , China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.0,"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/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.9279999732971191},{"id":"https://openalex.org/keywords/model-generation","display_name":"model generation","score":0.8019999861717224},{"id":"https://openalex.org/keywords/coverability","display_name":"coverability","score":0.8859999775886536},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.8709999918937683},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.6140000224113464},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.7039999961853027},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8056036233901978},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7247570753097534},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6589862704277039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141339898109436},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4990689754486084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46855267882347107},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4551957845687866},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4401475191116333},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.43466588854789734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10480943322181702},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.00316","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.00316","pdf_url":"https://arxiv.org/pdf/2206.00316","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2206.00316","doi":"https://doi.org/10.48550/arxiv.2206.00316","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.00316","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.00316","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.00316","pdf_url":"https://arxiv.org/pdf/2206.00316","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281697451.pdf","grobid_xml":"https://content.openalex.org/works/W4281697451.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387560012","https://openalex.org/W7160862963","https://openalex.org/W3205855746","https://openalex.org/W4401023970","https://openalex.org/W7127106504","https://openalex.org/W4382239152","https://openalex.org/W7162417724","https://openalex.org/W7162242017","https://openalex.org/W6960251684","https://openalex.org/W4417103359"],"abstract_inverted_index":{"Model-based":[0],"offline":[1,37,206,210],"optimization":[2],"with":[3,117,192],"dynamics-aware":[4,190],"policy":[5,11,19,57,191],"provides":[6,86],"a":[7,135,166,184,189],"new":[8],"perspective":[9],"for":[10,138,160],"learning":[12],"and":[13,83,85,127,150,174,198],"out-of-distribution":[14,52],"generalization,":[15],"where":[16],"the":[17,27,33,36,39,63,75,92,99,143,148,161,170],"learned":[18,40,100,218],"could":[20,42,95,179],"adapt":[21],"to":[22,32,49,58,72,120,154],"different":[23],"dynamics":[24,46,94,123],"enumerated":[25],"at":[26],"training":[28],"stage.":[29],"But":[30],"due":[31],"limitation":[34],"under":[35,147],"setting,":[38],"model":[41,171],"not":[43],"mimic":[44],"real":[45,76,93,122,162],"well":[47,91],"enough":[48],"support":[50],"reliable":[51],"exploration,":[53],"which":[54,102],"still":[55],"hinders":[56],"generalize":[59],"well.":[60],"To":[61,130],"narrow":[62],"gap,":[64],"previous":[65],"works":[66],"roughly":[67],"ensemble":[68],"randomly":[69],"initialized":[70],"models":[71,116,140,156],"better":[73,223,229],"approximate":[74],"dynamics.":[77,163],"However,":[78],"such":[79],"practice":[80],"is":[81],"costly":[82],"inefficient,":[84],"no":[87,195],"guarantee":[88],"on":[89,142,169,208],"how":[90],"be":[96],"approximated":[97],"by":[98,114,219],"models,":[101],"we":[103,133,187],"name":[104],"coverability":[105],"in":[106,124],"this":[107,112],"paper.":[108],"We":[109,164,213],"actively":[110],"address":[111],"issue":[113],"generating":[115],"provable":[118],"ability":[119],"cover":[121],"an":[125,152],"efficient":[126],"controllable":[128],"way.":[129],"that":[131,176,201,216],"end,":[132],"design":[134],"distance":[136],"metric":[137],"dynamic":[139],"based":[141],"occupancy":[144],"of":[145],"policies":[146,217],"dynamics,":[149],"propose":[151],"algorithm":[153,178,203],"generate":[155],"optimizing":[157],"their":[158,228],"coverage":[159],"give":[165],"theoretical":[167],"analysis":[168],"generation":[172],"process":[173],"proves":[175],"our":[177,202,220],"provide":[180],"enhanced":[181],"coverability.":[182],"As":[183],"downstream":[185],"task,":[186],"train":[188],"minor":[193],"or":[194],"conservative":[196],"penalty,":[197],"experiments":[199],"demonstrate":[200],"outperforms":[204],"prior":[205],"methods":[207],"existing":[209],"RL":[211],"benchmarks.":[212],"also":[214],"discover":[215],"method":[221],"have":[222],"zero-shot":[224],"transfer":[225],"performance,":[226],"implying":[227],"generalization.":[230]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2022-06-13T00:00:00"}