{"id":"https://openalex.org/W4229007060","doi":"https://doi.org/10.1017/s0263574722000650","title":"Learn multi-step object sorting tasks through deep reinforcement learning","display_name":"Learn multi-step object sorting tasks through deep reinforcement learning","publication_year":2022,"publication_date":"2022-05-06","ids":{"openalex":"https://openalex.org/W4229007060","doi":"https://doi.org/10.1017/s0263574722000650"},"language":"en","primary_location":{"id":"doi:10.1017/s0263574722000650","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0263574722000650","pdf_url":null,"source":{"id":"https://openalex.org/S92163612","display_name":"Robotica","issn_l":"0263-5747","issn":["0263-5747","1469-8668"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotica","raw_type":"journal-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/A5088571124","display_name":"J. Bao","orcid":"https://orcid.org/0000-0002-9476-5316"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]},{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiatong Bao","raw_affiliation_strings":["School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225000, China","School of Instrument Science and Engineering, Southeast University, Nanjing 210000, China"],"raw_orcid":"https://orcid.org/0000-0002-9476-5316","affiliations":[{"raw_affiliation_string":"School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225000, China","institution_ids":["https://openalex.org/I78978612"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing 210000, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419070","display_name":"Guoqing Zhang","orcid":"https://orcid.org/0000-0003-2090-2813"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Zhang","raw_affiliation_strings":["School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225000, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069225178","display_name":"Yi Peng","orcid":"https://orcid.org/0000-0001-7205-1200"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Peng","raw_affiliation_strings":["School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225000, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016324816","display_name":"Zhiyu Shao","orcid":"https://orcid.org/0000-0001-9337-4340"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Shao","raw_affiliation_strings":["School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225000, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048327458","display_name":"Aiguo Song","orcid":"https://orcid.org/0000-0002-1982-6780"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiguo Song","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing 210000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing 210000, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088571124"],"corresponding_institution_ids":["https://openalex.org/I76569877","https://openalex.org/I78978612"],"apc_list":null,"apc_paid":null,"fwci":1.2489,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82670426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"40","issue":"11","first_page":"3878","last_page":"3894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9984999895095825,"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":0.9890999794006348,"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":0.866562008857727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8147107362747192},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7660917043685913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7052643299102783},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.682693362236023},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6626312732696533},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6018282771110535},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4706368148326874},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4570889174938202},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4558982849121094},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4467794597148895},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.42301875352859497},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41713282465934753},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.09312409162521362},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08977457880973816},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08655673265457153}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.866562008857727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8147107362747192},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7660917043685913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7052643299102783},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.682693362236023},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6626312732696533},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6018282771110535},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4706368148326874},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4570889174938202},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4558982849121094},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4467794597148895},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.42301875352859497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41713282465934753},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.09312409162521362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08977457880973816},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08655673265457153},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s0263574722000650","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0263574722000650","pdf_url":null,"source":{"id":"https://openalex.org/S92163612","display_name":"Robotica","issn_l":"0263-5747","issn":["0263-5747","1469-8668"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotica","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W2082511574","https://openalex.org/W2108598243","https://openalex.org/W2145339207","https://openalex.org/W2557182326","https://openalex.org/W2784037720","https://openalex.org/W2913938871","https://openalex.org/W2946724987","https://openalex.org/W2951985238","https://openalex.org/W2962793652","https://openalex.org/W2963403593","https://openalex.org/W2963446712","https://openalex.org/W2968268581","https://openalex.org/W2990477050","https://openalex.org/W3008535267","https://openalex.org/W3035888914","https://openalex.org/W3044277051","https://openalex.org/W3081200565","https://openalex.org/W3086748961","https://openalex.org/W3089580269","https://openalex.org/W3092037789","https://openalex.org/W3094450719","https://openalex.org/W3101103779","https://openalex.org/W3101875589","https://openalex.org/W3130717831","https://openalex.org/W3131554325","https://openalex.org/W3134939669","https://openalex.org/W3184034462","https://openalex.org/W3200528739","https://openalex.org/W3200718608","https://openalex.org/W3207648387","https://openalex.org/W6790911039","https://openalex.org/W6798425039","https://openalex.org/W6801736874"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W4381094582","https://openalex.org/W1978893398","https://openalex.org/W1977906818","https://openalex.org/W2201908702","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2032776242"],"abstract_inverted_index":{"Abstract":[0],"Robotic":[1],"systems":[2],"are":[3,18,87,157],"usually":[4],"controlled":[5],"to":[6,55,58,89,106,113],"repetitively":[7],"perform":[8,59],"specific":[9],"actions":[10,123],"for":[11,96,149],"manufacturing":[12,44],"tasks.":[13],"The":[14,128],"traditional":[15],"control":[16],"methods":[17],"domain-dependent":[19],"and":[20,36,45,83,124,133,151,154],"model-dependent":[21],"with":[22],"cost":[23],"of":[24,34,99,122,141],"much":[25],"human":[26],"efforts.":[27],"They":[28],"cannot":[29],"meet":[30],"the":[31,139,142],"new":[32,104],"requirements":[33],"generality":[35],"flexibility":[37],"in":[38],"many":[39,120],"areas":[40],"such":[41],"as":[42,76],"intelligent":[43],"customized":[46],"production.":[47],"This":[48],"paper":[49],"develops":[50],"a":[51,91,103],"general":[52],"model-free":[53],"approach":[54],"enable":[56],"robots":[57],"multi-step":[60,115],"object":[61,135],"sorting":[62,116,136],"tasks":[63,117,137],"through":[64],"deep":[65],"reinforcement":[66],"learning.":[67],"Taking":[68],"projected":[69],"heightmap":[70],"images":[71],"from":[72],"different":[73],"time":[74],"steps":[75],"input":[77],"without":[78],"extra":[79],"high-level":[80],"image":[81],"analysis":[82],"understanding,":[84],"critic":[85,111],"models":[86,156],"designed":[88],"produce":[90],"pixel-wise":[92,108],"Q":[93,109],"value":[94],"map":[95],"each":[97],"type":[98],"action.":[100],"It":[101],"is":[102],"trial":[105],"apply":[107],"value-based":[110],"networks":[112],"solve":[114],"that":[118],"involve":[119],"types":[121],"complex":[125],"action":[126],"constraints.":[127],"experimental":[129],"validations":[130],"on":[131],"simulated":[132,150],"realistic":[134,152],"demonstrate":[138],"effectiveness":[140],"proposed":[143],"approach.":[144],"Qualitative":[145],"results":[146],"(videos),":[147],"code":[148],"experiments,":[153],"pre-trained":[155],"available":[158],"at":[159],"https://github.com/JiatongBao/DRLSorting":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}