{"id":"https://openalex.org/W3003496463","doi":"https://doi.org/10.1109/iros40897.2019.8968248","title":"TendencyRL: Multi-stage Discriminative Hints for Efficient Goal-Oriented Reverse Curriculum Learning","display_name":"TendencyRL: Multi-stage Discriminative Hints for Efficient Goal-Oriented Reverse Curriculum Learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3003496463","doi":"https://doi.org/10.1109/iros40897.2019.8968248","mag":"3003496463"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8968248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5100337545","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0002-1467-3594"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science","Department of Computer Science, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101069985","display_name":"Junfeng Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Ding","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science","Department of Computer Science, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776496","display_name":"Xiangyu Chen","orcid":"https://orcid.org/0000-0001-5858-5679"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science","Department of Computer Science, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112705513","display_name":"Zelin Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zelin Ye","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science","Department of Computer Science, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083734450","display_name":"Jialu Wang","orcid":"https://orcid.org/0000-0002-1982-0864"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialu Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science","Department of Computer Science, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079783943","display_name":"Ziruo Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziruo Cai","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science","Department of Computer Science, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010726528","display_name":"Cewu Lu","orcid":"https://orcid.org/0009-0003-7254-9318"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cewu Lu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science","Department of Computer Science, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100337545"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.4329,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73569578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"2019","issue":null,"first_page":"3474","last_page":"3480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9840999841690063,"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":0.9768000245094299,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7835733890533447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7688001394271851},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7399519681930542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7182556390762329},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6533617377281189},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5998592376708984},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5653367042541504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5335090160369873},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4764557182788849},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.4361015558242798},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4310639500617981},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37818050384521484},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0997740626335144}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7835733890533447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688001394271851},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7399519681930542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7182556390762329},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6533617377281189},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5998592376708984},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5653367042541504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5335090160369873},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4764557182788849},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.4361015558242798},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4310639500617981},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37818050384521484},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0997740626335144},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros40897.2019.8968248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"mag:3087405216","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002254779401664","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W187005120","https://openalex.org/W639708223","https://openalex.org/W779494576","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2126909264","https://openalex.org/W2155007355","https://openalex.org/W2218252352","https://openalex.org/W2285664202","https://openalex.org/W2397581010","https://openalex.org/W2398883595","https://openalex.org/W2417786368","https://openalex.org/W2601322194","https://openalex.org/W2602963933","https://openalex.org/W2603088459","https://openalex.org/W2606433045","https://openalex.org/W2613718673","https://openalex.org/W2751973545","https://openalex.org/W2755546070","https://openalex.org/W2962730405","https://openalex.org/W2963094133","https://openalex.org/W2963099939","https://openalex.org/W2963276097","https://openalex.org/W2963311874","https://openalex.org/W2963523627","https://openalex.org/W2963577640","https://openalex.org/W2963639957","https://openalex.org/W2963940579","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W6620707391","https://openalex.org/W6622487243","https://openalex.org/W6674884181","https://openalex.org/W6682849425","https://openalex.org/W6685757253","https://openalex.org/W6689158983","https://openalex.org/W6692846177","https://openalex.org/W6695998386","https://openalex.org/W6712227361","https://openalex.org/W6712392314","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6735677848","https://openalex.org/W6735789912","https://openalex.org/W6735944222","https://openalex.org/W6736368053","https://openalex.org/W6741302124","https://openalex.org/W6744181227","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,79,104],"algorithms":[3],"have":[4],"been":[5],"proven":[6],"successful":[7],"in":[8,100,135],"a":[9,34,52,77,87,93,101],"variety":[10],"of":[11,29,61,111],"simulation":[12],"tasks":[13,136],"with":[14,58,72,86,137],"dense":[15],"reward":[16,36,65,84],"feedback.":[17],"However,":[18],"real-world":[19],"RL":[20],"applications,":[21],"e.g.":[22],"robotic":[23],"manipulation,":[24],"remain":[25],"challenging":[26],"as":[27,121],"most":[28],"them":[30],"are":[31],"multi-stage":[32],"and":[33,123,130],"positive":[35],"can":[37,147],"only":[38],"be":[39],"received":[40],"when":[41],"the":[42,59,70,109,114],"final":[43],"goal":[44],"is":[45],"accomplished.":[46],"In":[47,141],"this":[48],"work,":[49],"we":[50,143],"propose":[51],"potential":[53],"solution":[54],"to":[55],"such":[56,120],"problems":[57],"introduction":[60],"an":[62],"experience-based":[63],"tendency":[64],"shaping":[66],"mechanism,":[67],"which":[68],"provides":[69],"robot":[71,150],"additional":[73],"hints":[74],"based":[75],"on":[76,80,113],"discriminative":[78],"past":[81],"experience.":[82],"The":[83],"along":[85],"stage-awareness":[88],"network":[89],"help":[90],"accelerate":[91],"solving":[92],"multistage":[94],"task":[95],"split":[96],"into":[97],"shorter":[98],"phases":[99],"reverse":[102],"curriculum":[103],"manner.":[105],"We":[106],"extensively":[107],"study":[108],"advantages":[110],"TRL":[112,126,146],"standard":[115],"long-term":[116],"goal-oriented":[117],"robotics":[118],"domains":[119],"pick-and-place,":[122],"show":[124],"that":[125,145],"performs":[127],"more":[128],"efficiently":[129],"robustly":[131],"than":[132],"prior":[133],"approaches":[134],"large":[138],"state":[139],"space.":[140],"addition,":[142],"demonstrate":[144],"solve":[148],"difficult":[149],"manipulation":[151],"challenges":[152],"directly":[153],"from":[154],"perception.":[155]},"counts_by_year":[{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
