{"id":"https://openalex.org/W3187939394","doi":"https://doi.org/10.24963/ijcai.2021/459","title":"Hindsight Trust Region Policy Optimization","display_name":"Hindsight Trust Region Policy Optimization","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3187939394","doi":"https://doi.org/10.24963/ijcai.2021/459","mag":"3187939394"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/459","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/459","pdf_url":"https://www.ijcai.org/proceedings/2021/0459.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0459.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074050672","display_name":"Hanbo Zhang","orcid":"https://orcid.org/0000-0002-2235-6855"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanbo Zhang","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Site Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Site Bai","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006277484","display_name":"Xuguang Lan","orcid":"https://orcid.org/0000-0002-3422-944X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082344124","display_name":"David Hsu","orcid":"https://orcid.org/0000-0002-2309-4535"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"David Hsu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3335","last_page":"3341"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.9793999791145325,"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/hindsight-bias","display_name":"Hindsight bias","score":0.994223415851593},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.7941921949386597},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7505360841751099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.667126476764679},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5826719403266907},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5346950888633728},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49155792593955994},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.48989051580429077},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4895938038825989},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.47375044226646423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44996142387390137},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.41709455847740173},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3879971504211426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2027590572834015},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.10258352756500244},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08484700322151184},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07741570472717285},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07171890139579773}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.994223415851593},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7941921949386597},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7505360841751099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.667126476764679},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5826719403266907},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5346950888633728},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49155792593955994},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.48989051580429077},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4895938038825989},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.47375044226646423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44996142387390137},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.41709455847740173},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3879971504211426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2027590572834015},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.10258352756500244},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08484700322151184},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07741570472717285},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07171890139579773},{"id":"https://openalex.org/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/459","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/459","pdf_url":"https://www.ijcai.org/proceedings/2021/0459.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/459","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/459","pdf_url":"https://www.ijcai.org/proceedings/2021/0459.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2993312730","display_name":null,"funder_award_id":"61973246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3917087662","display_name":null,"funder_award_id":"AISG2-RP-2020-016","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G4161133441","display_name":null,"funder_award_id":"AISG Award No: AISG2-RP-2020-016","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G5171785724","display_name":null,"funder_award_id":"No.62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5339301397","display_name":null,"funder_award_id":"91748208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187939394.pdf","grobid_xml":"https://content.openalex.org/works/W3187939394.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1191599655","https://openalex.org/W1514587017","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W2012587148","https://openalex.org/W2121863487","https://openalex.org/W2125612430","https://openalex.org/W2145339207","https://openalex.org/W2620974420","https://openalex.org/W2768498556","https://openalex.org/W2886380293","https://openalex.org/W2963014947","https://openalex.org/W2963277051","https://openalex.org/W2963864421","https://openalex.org/W2970393539","https://openalex.org/W2970948392","https://openalex.org/W3034296891","https://openalex.org/W3103780890","https://openalex.org/W4293872189","https://openalex.org/W4300799055"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W2139970489","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3148904318","https://openalex.org/W2136755647","https://openalex.org/W4385488867"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"with":[3,30,68,156],"sparse":[4,37,157],"rewards":[5],"is":[6],"a":[7,19,70,148],"major":[8],"challenge.":[9],"We":[10,60,95,105],"pro-":[11],"pose":[12],"Hindsight":[13,39,108],"Trust":[14],"Region":[15],"Policy":[16],"Optimization":[17],"(HTRPO),":[18],"new":[20],"RL":[21,155],"algorithm":[22,29,153],"that":[23,97,139],"extends":[24],"the":[25,34,42,57,62,74,79,115],"highly":[26],"successful":[27],"TRPO":[28],"hindsight":[31,63],"to":[32,41,45,73],"tackle":[33],"challenge":[35],"of":[36,65],"rewards.":[38,158],"refers":[40],"algorithm\u2019s":[43],"ability":[44],"learn":[46],"from":[47],"information":[48],"across":[49],"goals,":[50],"including":[51,129],"past":[52],"goals":[53],"not":[54],"intended":[55],"for":[56,118,154],"current":[58],"task.":[59],"derive":[61],"form":[64],"TRPO,":[66,143],"together":[67],"QKL,":[69],"quadratic":[71],"approximation":[72],"KL":[75,86],"divergence":[76,87],"constraint":[77],"on":[78,125],"trust":[80],"region.":[81],"QKL":[82],"reduces":[83],"variance":[84],"in":[85,92],"estimation":[88],"and":[89,132],"improves":[90,114],"stability":[91],"policy":[93,150],"updates.":[94],"show":[96,138],"HTRPO":[98,121,140],"has":[99,122],"similar":[100],"convergence":[101],"property":[102],"as":[103,144,146],"TRPO.":[104],"also":[106],"present":[107],"Goal":[109],"Filtering":[110],"(HGF),":[111],"which":[112],"further":[113],"learning":[116],"performance":[117],"suitable":[119],"tasks.":[120],"been":[123],"evaluated":[124],"various":[126],"sparse-reward":[127],"tasks,":[128],"Atari":[130],"games":[131],"simulated":[133],"robot":[134],"control.":[135],"Experimental":[136],"results":[137],"consistently":[141],"outperforms":[142],"well":[145],"HPG,":[147],"state-of-the-art":[149],"14":[151],"gradient":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}