{"id":"https://openalex.org/W4413917079","doi":"https://doi.org/10.1109/icra55743.2025.11127559","title":"Learning Dexterous Bimanual Catch Skills Through Adversarial-Cooperative Heterogeneous-Agent Reinforcement Learning","display_name":"Learning Dexterous Bimanual Catch Skills Through Adversarial-Cooperative Heterogeneous-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917079","doi":"https://doi.org/10.1109/icra55743.2025.11127559"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100400957","display_name":"Taewoo Kim","orcid":"https://orcid.org/0000-0003-0223-9317"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taewoo Kim","raw_affiliation_strings":["Social Robotics Research Section, Electronics and Telecommunications Research Institute (ETRI),Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Social Robotics Research Section, Electronics and Telecommunications Research Institute (ETRI),Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045112037","display_name":"Youngwoo Yoon","orcid":"https://orcid.org/0000-0003-4286-3421"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngwoo Yoon","raw_affiliation_strings":["Social Robotics Research Section, Electronics and Telecommunications Research Institute (ETRI),Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Social Robotics Research Section, Electronics and Telecommunications Research Institute (ETRI),Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100374317","display_name":"Jae\u2010Hong Kim","orcid":"https://orcid.org/0000-0003-2224-3516"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehong Kim","raw_affiliation_strings":["Social Robotics Research Section, Electronics and Telecommunications Research Institute (ETRI),Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Social Robotics Research Section, Electronics and Telecommunications Research Institute (ETRI),Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7930","last_page":"7936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8845000267028809,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8845000267028809,"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":0.8514999747276306,"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":0.7436444759368896},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7161583304405212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.654668390750885},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4629799723625183},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3711475431919098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3597748279571533},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16689276695251465}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7436444759368896},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7161583304405212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.654668390750885},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4629799723625183},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3711475431919098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3597748279571533},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16689276695251465},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1505952289","https://openalex.org/W2099618002","https://openalex.org/W2768629321","https://openalex.org/W2991046523","https://openalex.org/W4230037199","https://openalex.org/W4385430700","https://openalex.org/W4389352485"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"Robotic":[0],"catching":[1,24,54,123],"has":[2],"traditionally":[3],"focused":[4],"on":[5],"single-handed":[6],"systems,":[7],"which":[8],"are":[9],"limited":[10],"in":[11,38,97,108,122],"their":[12],"ability":[13],"to":[14,82,86,126],"handle":[15],"larger":[16],"or":[17],"more":[18],"complex":[19],"objects.":[20,111,135],"In":[21,42],"contrast,":[22],"bimanual":[23,53],"offers":[25],"significant":[26],"potential":[27],"for":[28,50],"improved":[29],"dexterity":[30],"and":[31,40,106],"object":[32],"handling":[33,109],"but":[34],"introduces":[35,63],"new":[36],"challenges":[37],"coordination":[39],"control.":[41],"this":[43],"paper,":[44],"we":[45],"propose":[46],"a":[47,69,78,116],"novel":[48],"framework":[49,96],"learning":[51],"dexterous":[52],"skills":[55],"using":[56,100],"Heterogeneous-Agent":[57],"Reinforcement":[58],"Learning":[59],"(HARL).":[60],"Our":[61,112],"approach":[62],"an":[64],"adversarial":[65],"reward":[66,124],"scheme,":[67],"where":[68],"throw":[70],"agent":[71,80],"increases":[72],"the":[73,95],"difficulty":[74],"of":[75],"throws-adjusting":[76],"speed-while":[77],"catch":[79,87],"learns":[81],"coordinate":[83],"both":[84],"hands":[85],"objects":[88],"under":[89],"these":[90],"evolving":[91],"conditions.":[92],"We":[93],"evaluate":[94],"simulated":[98],"environments":[99],"15":[101],"different":[102],"objects,":[103],"demonstrating":[104],"robustness":[105],"versatility":[107],"diverse":[110,134],"method":[113],"achieved":[114],"approximately":[115],"<tex":[117,130],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[118,131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2":[119],"x$</tex>":[120],"increase":[121],"compared":[125],"single-agent":[127],"baselines":[128],"across":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{1":[132],"5}$</tex>":[133]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}