{"id":"https://openalex.org/W4324266479","doi":"https://doi.org/10.1145/3579654.3579753","title":"Offline Imitation Learning Using Reward-free Exploratory Data","display_name":"Offline Imitation Learning Using Reward-free Exploratory Data","publication_year":2022,"publication_date":"2022-12-23","ids":{"openalex":"https://openalex.org/W4324266479","doi":"https://doi.org/10.1145/3579654.3579753"},"language":"en","primary_location":{"id":"doi:10.1145/3579654.3579753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579654.3579753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5007898304","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-2312-4247"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-2312-4247","affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-7587-8905","affiliations":[{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-1236-8318","affiliations":[{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044105981","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-6457-0625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Independent Researcher, China"],"raw_orcid":"https://orcid.org/0000-0001-6457-0625","affiliations":[{"raw_affiliation_string":"Independent Researcher, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"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":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.972100019454956,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.940500020980835,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8001275062561035},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7738099694252014},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6565855741500854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6141512989997864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5663905143737793},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.46788161993026733},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4551737904548645},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4489341676235199},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43314558267593384},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41127505898475647},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09289690852165222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001275062561035},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7738099694252014},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6565855741500854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141512989997864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5663905143737793},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.46788161993026733},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4551737904548645},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4489341676235199},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43314558267593384},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41127505898475647},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09289690852165222},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579654.3579753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579654.3579753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2174803659","https://openalex.org/W2963523627","https://openalex.org/W3033324992","https://openalex.org/W3036224891","https://openalex.org/W3037440645","https://openalex.org/W3101009114","https://openalex.org/W3131920644","https://openalex.org/W3214229832","https://openalex.org/W6780159193","https://openalex.org/W6791194670"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W3203657119"],"abstract_inverted_index":{"Offline":[0],"imitative":[1],"learning(OIL)":[2],"is":[3,24,68,135,145],"often":[4],"used":[5,51,136],"to":[6,27,41,137,147,151],"solve":[7],"complex":[8],"continuous":[9,166],"decision-making":[10],"tasks.":[11,88],"For":[12],"these":[13],"tasks":[14,168],"such":[15,160],"as":[16,161],"robot":[17],"control,":[18],"automatic":[19],"driving":[20],"and":[21,37,74,117,131],"etc.,":[22],"it":[23],"either":[25],"difficult":[26],"design":[28],"an":[29,82,107,143],"effective":[30,83],"reward":[31,84,133],"for":[32,39],"learning":[33,61,101,110],"or":[34],"very":[35],"expensive":[36],"time-consuming":[38],"agents":[40],"collect":[42],"data":[43,50,97,122],"interactively":[44],"with":[45,114,185],"the":[46,49,78,94,115,139,149,153,171],"environment.":[47],"However,":[48],"in":[52,86],"previous":[53,186],"OIL":[54],"methods":[55],"are":[56],"all":[57],"gathered":[58],"by":[59,64,112],"reinforcement":[60,109],"algorithms":[62],"guided":[63],"task-specific":[65,191],"rewards,":[66],"which":[67],"not":[69],"a":[70,126,156],"true":[71],"reward-free":[72,95],"premise":[73],"still":[75],"suffers":[76],"from":[77],"problem":[79],"of":[80],"designing":[81],"function":[85,134],"real":[87],"To":[89],"this":[90],"end,":[91],"we":[92],"propose":[93],"exploratory":[96],"driven":[98],"offline":[99],"imitation":[100,177],"(ExDOIL)":[102],"framework.":[103],"ExDOIL":[104],"first":[105],"trains":[106],"unsupervised":[108,120],"agent":[111,144],"interacting":[113],"environment,":[116],"collects":[118],"enough":[119],"exploration":[121],"during":[123],"training;":[124],"Then,":[125],"task":[127,154],"independent":[128],"yet":[129],"simple":[130],"efficient":[132],"relabel":[138],"collected":[140],"data;":[141],"Finally,":[142],"trained":[146],"imitate":[148],"expert":[150],"complete":[152],"through":[155],"conventional":[157],"RL":[158],"algorithm":[159],"TD3.":[162],"Extensive":[163],"experiments":[164],"on":[165,182],"control":[167],"demonstrate":[169],"that":[170],"proposed":[172],"framework":[173],"can":[174],"achieve":[175],"better":[176],"performance(28%":[178],"higher":[179],"episode":[180],"returns":[181],"average)":[183],"comparing":[184],"SOTA":[187],"method(ORIL)":[188],"without":[189],"any":[190],"rewards.":[192]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}