{"id":"https://openalex.org/W4313160956","doi":"https://doi.org/10.1109/iros47612.2022.9981869","title":"Backward Imitation and Forward Reinforcement Learning via Bi-directional Model Rollouts","display_name":"Backward Imitation and Forward Reinforcement Learning via Bi-directional Model Rollouts","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4313160956","doi":"https://doi.org/10.1109/iros47612.2022.9981869"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981869","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5039585469","display_name":"Yuxin Pan","orcid":"https://orcid.org/0000-0002-6015-0110"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuxin Pan","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Division of Emerging Interdisciplinary Areas under IPO,Hong Kong","Division of Emerging Interdisciplinary Areas under IPO, The Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Division of Emerging Interdisciplinary Areas under IPO,Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Division of Emerging Interdisciplinary Areas under IPO, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102011179","display_name":"Fangzhen Lin","orcid":"https://orcid.org/0000-0002-3141-8675"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fangzhen Lin","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong","Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"9040","last_page":"9047"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9821000099182129,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9685999751091003,"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":0.878250777721405},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7690796852111816},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6896147727966309},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5262895226478577},{"id":"https://openalex.org/keywords/value-network","display_name":"Value network","score":0.5084182620048523},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.45996055006980896},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4261630177497864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39733263850212097},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24603360891342163}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.878250777721405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690796852111816},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6896147727966309},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5262895226478577},{"id":"https://openalex.org/C89249532","wikidata":"https://www.wikidata.org/wiki/Q7912758","display_name":"Value network","level":3,"score":0.5084182620048523},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.45996055006980896},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4261630177497864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39733263850212097},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24603360891342163},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C4216890","wikidata":"https://www.wikidata.org/wiki/Q815823","display_name":"Business model","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros47612.2022.9981869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981869","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-123198","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-123198","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1971984830","https://openalex.org/W1980035368","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2593414223","https://openalex.org/W2837605352","https://openalex.org/W2941534112","https://openalex.org/W2953708620","https://openalex.org/W3089952679","https://openalex.org/W3205868665","https://openalex.org/W4214709514","https://openalex.org/W4288319859","https://openalex.org/W4297703537","https://openalex.org/W4298206671","https://openalex.org/W6638018090","https://openalex.org/W6734385456","https://openalex.org/W6737937804","https://openalex.org/W6747473740","https://openalex.org/W6749504895","https://openalex.org/W6750007414","https://openalex.org/W6751494529","https://openalex.org/W6764053384","https://openalex.org/W6768607713","https://openalex.org/W6771656438","https://openalex.org/W6772285785","https://openalex.org/W6779142360","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W3201942433"],"abstract_inverted_index":{"Traditional":[0],"model-based":[1,24,63,262],"reinforcement":[2,143],"learning":[3,144],"(RL)":[4],"methods":[5],"generate":[6,54],"forward":[7,74,142,166],"rollout":[8,56,111,152,167],"traces":[9,112,153],"using":[10],"the":[11,19,28,37,41,45,49,65,82,85,93,97,107,127,131,138,148,158,175,194,215,223,228,235,244,250],"learnt":[12],"dynamics":[13],"model":[14,34],"to":[15,30,52,80,129,177,180,213,234],"reduce":[16],"interactions":[17],"with":[18],"real":[20,195],"environment.":[21],"The":[22],"recent":[23],"RL":[25,87],"method":[26],"considers":[27],"way":[29],"learn":[31],"a":[32,187,206],"backward":[33,55,69,110,139,151],"that":[35,109,241],"specifies":[36],"conditional":[38],"probability":[39],"of":[40,62,160],"previous":[42,46],"state":[43,51],"given":[44],"action":[47],"and":[48,71,96,121,141,163,181,191,248],"current":[50],"additionally":[53],"trajectories.":[57],"However,":[58],"in":[59,186],"this":[60,134],"type":[61],"method,":[64],"samples":[66],"derived":[67],"from":[68,73,117,183],"rollouts":[70,75],"those":[72],"are":[76,113,122,219],"simply":[77],"aggregated":[78],"together":[79],"optimize":[81],"policy":[83,170],"via":[84],"model-free":[86],"algorithm,":[88],"which":[89,218],"may":[90],"decrease":[91],"both":[92,178],"sample":[94,246],"efficiency":[95,247],"convergence":[98],"rate.":[99],"This":[100],"is":[101,211,232],"because":[102],"such":[103],"an":[104],"approach":[105],"ignores":[106],"fact":[108],"often":[114],"generated":[115],"starting":[116],"some":[118],"high-value":[119,184],"states":[120,185,217],"certainly":[123],"more":[124,188,200],"instructive":[125],"for":[126,157,169,202],"agent":[128,149,176],"improve":[130],"behavior.":[132],"In":[133],"paper,":[135],"we":[136,226,239],"propose":[137],"imitation":[140,159],"(BIFRL)":[145],"framework":[146],"where":[147,230],"treats":[150],"as":[154],"expert":[155],"demonstrations":[156],"excellent":[161],"behaviors,":[162],"then":[164],"collects":[165],"transitions":[168],"reinforcement.":[171],"Consequently,":[172],"BIFRL":[173,231,242],"empowers":[174],"reach":[179],"explore":[182],"efficient":[189],"manner,":[190],"further":[192],"reduces":[193],"interactions,":[196],"making":[197],"it":[198],"potentially":[199],"suitable":[201],"real-robot":[203],"learning.":[204],"Moreover,":[205],"value-regularized":[207],"generative":[208],"adversarial":[209],"network":[210],"introduced":[212],"augment":[214],"valuable":[216],"infrequently":[220],"received":[221],"by":[222],"agent.":[224],"Theoretically,":[225],"provide":[227],"condition":[229],"superior":[233],"baseline":[236],"methods.":[237,263],"Experimentally,":[238],"demonstrate":[240],"acquires":[243],"better":[245],"produces":[249],"competitive":[251],"asymptotic":[252],"performance":[253],"on":[254],"various":[255],"MuJoCo":[256],"locomotion":[257],"tasks":[258],"compared":[259],"against":[260],"state-of-the-art":[261]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}