{"id":"https://openalex.org/W6996465431","doi":null,"title":"The Role of Dataset Generation in Offline Reinforcement Learning","display_name":"The Role of Dataset Generation in Offline Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W6996465431"},"language":"en","primary_location":{"id":"pmh:oai:epub.jku.at/:6785210","doi":null,"is_oa":false,"landing_page_url":"https://resolver.obvsg.at/urn:nbn:at:at-ubl:1-46204","pdf_url":null,"source":{"id":"https://openalex.org/S4306401788","display_name":"University Library Linz repository (Johannes Kepler Universitat Linz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I121883995","host_organization_name":"Johannes Kepler University of Linz","host_organization_lineage":["https://openalex.org/I121883995"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"parent_works":[],"lineage":["https://openalex.org/W6996465431"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5008919064","display_name":"Kajetan Schweighofer","orcid":"https://orcid.org/0009-0001-0482-2699","observed_orcids":["https://orcid.org/0009-0001-0482-2699"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Schweighofer, Kajetan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5008919064"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":true,"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/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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/dataset-composition","display_name":"dataset composition","score":0.9399999976158142},{"id":"https://openalex.org/keywords/behavioral-cloning","display_name":"behavior cloning","score":0.9459999799728394},{"id":"https://openalex.org/keywords/discrete-action-space","display_name":"discrete action space","score":0.765999972820282}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8985000252723694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469000220298767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.660099983215332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6597999930381775},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6049000024795532},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.4219000041484833},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.39469999074935913},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:epub.jku.at/:6785210","doi":null,"is_oa":false,"landing_page_url":"https://resolver.obvsg.at/urn:nbn:at:at-ubl:1-46204","pdf_url":null,"source":{"id":"https://openalex.org/S4306401788","display_name":"University Library Linz repository (Johannes Kepler Universitat Linz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I121883995","host_organization_name":"Johannes Kepler University of Linz","host_organization_lineage":["https://openalex.org/I121883995"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3213037073","https://openalex.org/W4285414997","https://openalex.org/W3215847557","https://openalex.org/W4415270767","https://openalex.org/W7124281208","https://openalex.org/W4407245331","https://openalex.org/W3017362854","https://openalex.org/W4360764815","https://openalex.org/W4381797986","https://openalex.org/W7133215161"],"abstract_inverted_index":{"Offline":[0,75,188,211],"Reinforcement":[1,7,76,189,212],"Learning":[2,77,190],"is":[3,83,87,111,180],"a":[4,218],"sub-field":[5],"of":[6,24,29,38,44,65,68,74,102,117,124],"Learning,":[8,213],"where":[9],"policies":[10,197],"are":[11,201],"learned":[12,40,145],"from":[13],"logged":[14],"interactions":[15,19],"alone.":[16],"Dispensing":[17],"direct":[18],"makes":[20],"the":[21,25,30,36,39,57,66,72,92,96,100,103,109,118,125,132,144,148,153,185],"dataset":[22,45,69,110,133,154],"one":[23],"most":[26],"essential":[27],"parts":[28],"algorithm,":[31],"having":[32],"large":[33],"influence":[34],"on":[35,71,131],"performance":[37,73],"policy.":[41],"The":[42],"effects":[43],"compositions":[46],"have":[47,135,174],"mostly":[48],"been":[49],"disregarded":[50],"when":[51],"comparing":[52],"recent":[53],"algorithmic":[54],"advances":[55],"in":[56],"field.":[58],"Towards":[59],"that":[60,122,151,173,196,206],"end,":[61],"an":[62],"empirical":[63],"analysis":[64],"effect":[67],"composition":[70,86],"algorithms":[78,142],"for":[79],"discrete":[80],"action":[81],"environments":[82],"conducted.":[84],"Dataset":[85],"evaluated":[88],"through":[89],"two":[90],"metrics,":[91],"Trajectory":[93,164,176,221],"Quality":[94,222],"and":[95,223],"State-Action":[97,137,167,224],"Coverage.":[98,138,225],"Furthermore,":[99,192],"Entropy":[101],"behavioral":[104,149],"policy":[105,146,150],"used":[106],"to":[107,113,134,140,203],"create":[108,204],"linked":[112],"those":[114,215],"metrics.":[115],"\\nAnalysis":[116],"conducted":[119],"experiments":[120],"suggest":[121],"variants":[123],"off-policy":[126],"Deep":[127],"Q-Network":[128],"family":[129],"rely":[130],"high":[136,163,166,175],"Contrary":[139],"that,":[141],"constraining":[143],"towards":[147],"generated":[152],"perform":[155],"well":[156],"across":[157],"datasets,":[158],"if":[159],"they":[160],"exhibit":[161],"either":[162],"Quality,":[165,177],"Coverage":[168],"or":[169],"both.":[170],"On":[171],"datasets":[172,205,216],"Behavioral":[178],"Cloning":[179],"performing":[181],"as":[182,184,214],"good":[183],"best":[186],"considered":[187],"algorithms.":[191],"it":[193],"was":[194],"found":[195],"with":[198,210],"intermediate":[199],"entropy":[200],"desirable":[202],"can":[207],"be":[208],"leveraged":[209],"pose":[217],"tradeoff":[219],"between":[220]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}