{"id":"https://openalex.org/W3175584021","doi":"https://doi.org/10.1109/tnnls.2021.3088947","title":"Complex Robotic Manipulation via Graph-Based Hindsight Goal Generation","display_name":"Complex Robotic Manipulation via Graph-Based Hindsight Goal Generation","publication_year":2021,"publication_date":"2021-06-28","ids":{"openalex":"https://openalex.org/W3175584021","doi":"https://doi.org/10.1109/tnnls.2021.3088947","mag":"3175584021","pmid":"https://pubmed.ncbi.nlm.nih.gov/34181552"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3088947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3088947","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mediatum.ub.tum.de/1615882","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060444894","display_name":"Zhenshan Bing","orcid":"https://orcid.org/0000-0002-0896-2517"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Zhenshan Bing","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000619320","display_name":"Matthias Brucker","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Brucker","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088159741","display_name":"Fabrice O. Morin","orcid":"https://orcid.org/0000-0003-0185-7420"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabrice O. Morin","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448563","display_name":"Rui Li","orcid":"https://orcid.org/0000-0002-8877-8524"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Li","raw_affiliation_strings":["School of Automation, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053561890","display_name":"Xiaojie Su","orcid":"https://orcid.org/0000-0003-1802-0264"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Su","raw_affiliation_strings":["School of Automation, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768452","display_name":"Kai Huang","orcid":"https://orcid.org/0000-0003-0359-7810"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Huang","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5060444894"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":3.639,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94017786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"33","issue":"12","first_page":"7863","last_page":"7876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9857000112533569,"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":0.9787840247154236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7555827498435974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5650899410247803},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5554467439651489},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5095193982124329},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5080325603485107},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4695744216442108},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.4392507076263428},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41492339968681335},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2697933316230774},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09222099184989929}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9787840247154236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555827498435974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5650899410247803},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5554467439651489},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5095193982124329},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5080325603485107},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4695744216442108},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.4392507076263428},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41492339968681335},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2697933316230774},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09222099184989929},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2021.3088947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3088947","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34181552","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34181552","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:mediatum.ub.tum.de:node/1615882","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1615882","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1615882","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1615882","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6483959550","display_name":null,"funder_award_id":"945539","funder_id":"https://openalex.org/F4320338336","funder_display_name":"H2020 Future and Emerging Technologies"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338336","display_name":"H2020 Future and Emerging Technologies","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1949804828","https://openalex.org/W2125612430","https://openalex.org/W2139612737","https://openalex.org/W2155007355","https://openalex.org/W2163922914","https://openalex.org/W2169528473","https://openalex.org/W2201581102","https://openalex.org/W2529601334","https://openalex.org/W2541678333","https://openalex.org/W2603088459","https://openalex.org/W2616430965","https://openalex.org/W2623491082","https://openalex.org/W2742454413","https://openalex.org/W2744921630","https://openalex.org/W2768956845","https://openalex.org/W2772589676","https://openalex.org/W2774852867","https://openalex.org/W2786917922","https://openalex.org/W2804010078","https://openalex.org/W2810957722","https://openalex.org/W2859967432","https://openalex.org/W2901747954","https://openalex.org/W2905606790","https://openalex.org/W2921547827","https://openalex.org/W2946723315","https://openalex.org/W2962765321","https://openalex.org/W2963099939","https://openalex.org/W2963311874","https://openalex.org/W2963321092","https://openalex.org/W2963523627","https://openalex.org/W2964097858","https://openalex.org/W2969456553","https://openalex.org/W2970393539","https://openalex.org/W2970948392","https://openalex.org/W2978938326","https://openalex.org/W2982432464","https://openalex.org/W3043763914","https://openalex.org/W4232849097","https://openalex.org/W4288331462","https://openalex.org/W4289440819","https://openalex.org/W4293872189","https://openalex.org/W4294336468","https://openalex.org/W4297795006","https://openalex.org/W4297809330","https://openalex.org/W4300799055","https://openalex.org/W6682849425","https://openalex.org/W6687681856","https://openalex.org/W6735789912","https://openalex.org/W6737937804","https://openalex.org/W6739193204","https://openalex.org/W6740801417","https://openalex.org/W6741302124","https://openalex.org/W6742667875","https://openalex.org/W6748599296","https://openalex.org/W6750007414","https://openalex.org/W6751087324","https://openalex.org/W6752217255","https://openalex.org/W6753183898","https://openalex.org/W6755289019","https://openalex.org/W6756293349","https://openalex.org/W6757438168","https://openalex.org/W6762640273","https://openalex.org/W6762868464","https://openalex.org/W6763356705","https://openalex.org/W6764173040","https://openalex.org/W6766694020","https://openalex.org/W6767047803","https://openalex.org/W6767246565"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3148904318","https://openalex.org/W2139970489","https://openalex.org/W2022803902","https://openalex.org/W4297427155"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"algorithms,":[2],"such":[3,128,155],"as":[4],"hindsight":[5,10,35,168,177],"experience":[6,39],"replay":[7],"(HER)":[8],"and":[9,71,212,220],"goal":[11,169],"generation":[12,170],"(HGG),":[13],"have":[14],"been":[15],"able":[16],"to":[17,53,65,73,75,88,109],"solve":[18,143,154],"challenging":[19,46,200],"robotic":[20],"manipulation":[21,110,144,201],"tasks":[22,47,89,111,145,156,202],"in":[23,45,48,67,78,90,127,160,183,208],"multigoal":[24],"settings":[25],"with":[26,40,112,132,146,203],"sparse":[27],"rewards.":[28],"HER":[29,57],"achieves":[30],"its":[31],"training":[32],"success":[33,214],"through":[34],"replays":[36],"of":[37,135,174,192],"past":[38],"heuristic":[41],"goals":[42,50,61,77,93,178],"but":[43],"underperforms":[44],"which":[49,91,187],"are":[51,63,94,216],"difficult":[52],"explore.":[54],"HGG":[55,86,105,120,141,175,219],"enhances":[56],"by":[58],"selecting":[59,176],"intermediate":[60],"that":[62,152],"easy":[64],"achieve":[66],"the":[68,79,98,103,115,133,193],"short":[69],"term":[70],"promising":[72],"lead":[74],"target":[76,92],"long":[80],"term.":[81],"This":[82],"guided":[83],"exploration":[84],"makes":[85],"applicable":[87,108],"far":[95],"away":[96],"from":[97],"object's":[99],"initial":[100],"position.":[101],"However,":[102],"vanilla":[104],"is":[106,121,158,188],"not":[107,122],"obstacles":[113],"because":[114],"Euclidean":[116],"metric":[117,126],"used":[118],"for":[119],"an":[123,129,172,184],"accurate":[124],"distance":[125,138],"environment.":[130,194],"Although,":[131],"guidance":[134],"a":[136,148,189],"handcrafted":[137],"grid,":[139],"grid-based":[140],"can":[142,153,223],"obstacles,":[147,204],"more":[149],"feasible":[150],"method":[151],"automatically":[157],"still":[159],"demand.":[161],"In":[162],"this":[163],"article,":[164],"we":[165],"propose":[166],"graph-based":[167],"(G-HGG),":[171],"extension":[173],"based":[179],"on":[180,198],"shortest":[181],"distances":[182],"obstacle-avoiding":[185],"graph,":[186],"discrete":[190],"representation":[191],"We":[195],"evaluated":[196],"G-HGG":[197],"four":[199],"where":[205],"significant":[206],"enhancements":[207],"both":[209],"sample":[210],"efficiency":[211],"overall":[213],"rate":[215],"shown":[217],"over":[218],"HER.":[221],"Videos":[222],"be":[224],"viewed":[225],"at":[226],"https://videoviewsite.wixsite.com/ghgg.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}