{"id":"https://openalex.org/W3009379771","doi":"https://doi.org/10.1109/iros45743.2020.9341578","title":"Deep Adversarial Reinforcement Learning for Object Disentangling","display_name":"Deep Adversarial Reinforcement Learning for Object Disentangling","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3009379771","doi":"https://doi.org/10.1109/iros45743.2020.9341578","mag":"3009379771"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.03779","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025962742","display_name":"Melvin Laux","orcid":"https://orcid.org/0000-0003-3517-7386"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Melvin Laux","raw_affiliation_strings":["TU Darmstadt,Intelligent Autonomous Systems,Germany","TU Darmstadt, Intelligent Autonomous Systems, Germany"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt,Intelligent Autonomous Systems,Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"TU Darmstadt, Intelligent Autonomous Systems, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014519249","display_name":"Oleg Arenz","orcid":"https://orcid.org/0000-0002-9470-2833"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oleg Arenz","raw_affiliation_strings":["TU Darmstadt,Intelligent Autonomous Systems,Germany","TU Darmstadt, Intelligent Autonomous Systems, Germany"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt,Intelligent Autonomous Systems,Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"TU Darmstadt, Intelligent Autonomous Systems, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["TU Darmstadt,Intelligent Autonomous Systems,Germany","TU Darmstadt, Intelligent Autonomous Systems, Germany"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt,Intelligent Autonomous Systems,Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"TU Darmstadt, Intelligent Autonomous Systems, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017983137","display_name":"Joni Pajarinen","orcid":"https://orcid.org/0000-0003-4469-8191"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joni Pajarinen","raw_affiliation_strings":["TU Darmstadt,Intelligent Autonomous Systems,Germany","TU Darmstadt, Intelligent Autonomous Systems, Germany"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt,Intelligent Autonomous Systems,Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"TU Darmstadt, Intelligent Autonomous Systems, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025962742"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02186123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1604 7316","issue":null,"first_page":"5504","last_page":"5510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9894999861717224,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9117966890335083},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.761324405670166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7477264404296875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7307256460189819},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.7234159708023071},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6768065690994263},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6540830135345459},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6059356927871704},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4443252980709076},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44134238362312317},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.431281715631485},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.4259367883205414},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3433791697025299},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11831259727478027},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07500413060188293}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9117966890335083},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.761324405670166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7477264404296875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307256460189819},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.7234159708023071},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6768065690994263},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6540830135345459},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6059356927871704},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4443252980709076},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44134238362312317},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.431281715631485},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.4259367883205414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3433791697025299},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11831259727478027},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07500413060188293},{"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/iros45743.2020.9341578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:tuprints.ulb.tu-darmstadt.de:22926","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401590","display_name":"Technischen Universit\u00e4t Darmstadt","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:arXiv.org:2003.03779","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.03779","pdf_url":"https://arxiv.org/pdf/2003.03779","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3009379771","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.03779.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:135372","is_oa":false,"landing_page_url":"https://tuprints.ulb.tu-darmstadt.de/22926","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:147579","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/147579/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"},{"id":"doi:10.48550/arxiv.2003.03779","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.03779","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.26083/tuprints-00022926","is_oa":true,"landing_page_url":"https://doi.org/10.26083/tuprints-00022926","pdf_url":null,"source":{"id":"https://openalex.org/S7407051655","display_name":"TUprints","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.03779","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.03779","pdf_url":"https://arxiv.org/pdf/2003.03779","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323384","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W2047191624","https://openalex.org/W2099471712","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2342840547","https://openalex.org/W2601066903","https://openalex.org/W2602963933","https://openalex.org/W2616430965","https://openalex.org/W2772709170","https://openalex.org/W2773525213","https://openalex.org/W2773691349","https://openalex.org/W2785962646","https://openalex.org/W2908460759","https://openalex.org/W2928153079","https://openalex.org/W2949103145","https://openalex.org/W2963207607","https://openalex.org/W2963277051","https://openalex.org/W2963293881","https://openalex.org/W2963311874","https://openalex.org/W2963577640","https://openalex.org/W2963684914","https://openalex.org/W2963713397","https://openalex.org/W2967292964","https://openalex.org/W2981030070","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2996343955","https://openalex.org/W3037207827","https://openalex.org/W3039584045","https://openalex.org/W6637967152","https://openalex.org/W6640425456","https://openalex.org/W6704559304","https://openalex.org/W6718092244","https://openalex.org/W6733049761","https://openalex.org/W6735677848","https://openalex.org/W6735789912","https://openalex.org/W6741302124","https://openalex.org/W6746177919","https://openalex.org/W6746700722","https://openalex.org/W6747027214","https://openalex.org/W6757592117","https://openalex.org/W6757645525","https://openalex.org/W6762427411","https://openalex.org/W6772005887","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3133374884","https://openalex.org/W2973387504","https://openalex.org/W3090910462","https://openalex.org/W3213728790","https://openalex.org/W3035756007","https://openalex.org/W3203483019","https://openalex.org/W2952672470","https://openalex.org/W2964198579","https://openalex.org/W2947525798","https://openalex.org/W3201617237","https://openalex.org/W2914584948","https://openalex.org/W2735268712","https://openalex.org/W2528734395","https://openalex.org/W2910219310","https://openalex.org/W2733961795","https://openalex.org/W2513373085","https://openalex.org/W2953129341","https://openalex.org/W2889878992","https://openalex.org/W1972063518","https://openalex.org/W3135512538"],"abstract_inverted_index":{"Deep":[0],"learning":[1,22,92],"in":[2,17,177],"combination":[3],"with":[4,162],"improved":[5],"training":[6,142,147],"techniques":[7],"and":[8,24,118],"high":[9],"computational":[10],"power":[11],"has":[12],"led":[13],"to":[14,25,104,111,122,125,127,143,154],"recent":[15],"advances":[16],"the":[18,62,66,69,74,76,106,109,116,119,128,174],"field":[19],"of":[20,65,131],"reinforcement":[21,91],"(RL)":[23],"successful":[26],"robotic":[27,36],"RL":[28,37,77],"applications":[29],"such":[30],"as":[31],"in-hand":[32],"manipulation.":[33],"However,":[34],"most":[35],"relies":[38],"on":[39],"a":[40,88,156,163],"well":[41],"known":[42],"initial":[43,183],"state":[44],"distribution.":[45],"In":[46],"real-world":[47],"tasks,":[48],"this":[49,84],"information":[50],"is":[51,102],"however":[52],"often":[53],"not":[54,72],"available.":[55],"For":[56],"example,":[57],"when":[58,179],"disentangling":[59,159,178],"waste":[60],"objects":[61,70],"actual":[63],"position":[64],"robot":[67,152,167],"w.r.t.":[68],"may":[71],"match":[73],"positions":[75],"policy":[78,130],"was":[79],"trained":[80,103],"for.":[81],"To":[82],"solve":[83,155],"problem,":[85],"we":[86],"present":[87],"novel":[89],"adversarial":[90],"(ARL)":[93],"framework.":[94],"The":[95],"ARL":[96],"framework":[97],"utilizes":[98],"an":[99,148],"adversary,":[100],"which":[101],"steer":[105],"original":[107],"agent,":[108],"protagonist,":[110],"challenging":[112,157],"states.":[113],"We":[114,134],"train":[115],"protagonist":[117],"adversary":[120],"jointly":[121],"allow":[123],"them":[124],"adapt":[126],"changing":[129],"their":[132],"opponent.":[133],"show":[135,169],"that":[136,170],"our":[137,171],"method":[138,176],"can":[139],"generalize":[140],"from":[141,181],"test":[144],"scenarios":[145],"by":[146],"end-to-end":[149],"system":[150],"for":[151],"control":[153],"object":[158],"task.":[160],"Experiments":[161],"KUKA":[164],"LBR+":[165],"7-DOF":[166],"arm":[168],"approach":[172],"outperforms":[173],"baseline":[175],"starting":[180],"different":[182],"states":[184],"than":[185],"provided":[186],"during":[187],"training.":[188]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
