{"id":"https://openalex.org/W4312799247","doi":"https://doi.org/10.1109/iros47612.2022.9981763","title":"Safe adaptation in multiagent competition","display_name":"Safe adaptation in multiagent competition","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312799247","doi":"https://doi.org/10.1109/iros47612.2022.9981763"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981763","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5040251822","display_name":"Macheng Shen","orcid":"https://orcid.org/0000-0002-1440-6904"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Macheng Shen","raw_affiliation_strings":["Massachusetts Institute of Technology,Department of Mechanical Engineering,Cambridge,MA,USA,02139"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Department of Mechanical Engineering,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["Massachusetts Institute of Technology,Department of Aeronautics and Astronautics,Cambridge,MA,USA,02139"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Department of Aeronautics and Astronautics,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I46020346","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040251822"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16106443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"12441","last_page":"12447"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9973000288009644,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9670000076293945,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8549320697784424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7467296123504639},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.7355657815933228},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6817187070846558},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.664754331111908},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6111442446708679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6027180552482605},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5465726852416992},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5221543312072754},{"id":"https://openalex.org/keywords/id-ego-and-super-ego","display_name":"Id, ego and super-ego","score":0.5126509070396423},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.4141894578933716},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3295687139034271},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.17568913102149963},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1432669460773468},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11903485655784607},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08639177680015564}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8549320697784424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7467296123504639},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.7355657815933228},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6817187070846558},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.664754331111908},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6111442446708679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6027180552482605},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5465726852416992},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5221543312072754},{"id":"https://openalex.org/C9180747","wikidata":"https://www.wikidata.org/wiki/Q486893","display_name":"Id, ego and super-ego","level":2,"score":0.5126509070396423},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.4141894578933716},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3295687139034271},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.17568913102149963},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1432669460773468},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11903485655784607},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08639177680015564},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981763","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":51,"referenced_works":["https://openalex.org/W1499339896","https://openalex.org/W1542941925","https://openalex.org/W1967438932","https://openalex.org/W2067050450","https://openalex.org/W2257979135","https://openalex.org/W2578206533","https://openalex.org/W2612780607","https://openalex.org/W2622408375","https://openalex.org/W2736601468","https://openalex.org/W2794363191","https://openalex.org/W2810602713","https://openalex.org/W2904455790","https://openalex.org/W2914304175","https://openalex.org/W2963277051","https://openalex.org/W2966128956","https://openalex.org/W2982316857","https://openalex.org/W2996808613","https://openalex.org/W3020156139","https://openalex.org/W3099518626","https://openalex.org/W3117215073","https://openalex.org/W3163926178","https://openalex.org/W3210807411","https://openalex.org/W4287899365","https://openalex.org/W4297789683","https://openalex.org/W4299802797","https://openalex.org/W4301602852","https://openalex.org/W4320013936","https://openalex.org/W6718092244","https://openalex.org/W6721101288","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6737726454","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6743367460","https://openalex.org/W6744562401","https://openalex.org/W6745190604","https://openalex.org/W6745777752","https://openalex.org/W6747473740","https://openalex.org/W6748910126","https://openalex.org/W6750222692","https://openalex.org/W6751912414","https://openalex.org/W6756463683","https://openalex.org/W6757223306","https://openalex.org/W6762427411","https://openalex.org/W6773882092","https://openalex.org/W6775695405","https://openalex.org/W6781640943","https://openalex.org/W6784341771","https://openalex.org/W6795908048","https://openalex.org/W6803550857"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W2573831620"],"abstract_inverted_index":{"Achieving":[0],"the":[1,42,46,49,60,68,99,115,118,126,145,149],"capability":[2],"of":[3,80,117],"adapting":[4],"to":[5,30,32,56,66,82,144,158],"ever-changing":[6],"environments":[7],"is":[8,54,101,151],"a":[9,78,93,104],"critical":[10],"step":[11],"towards":[12],"building":[13],"fully":[14],"autonomous":[15],"robots":[16],"that":[17,137,148],"operate":[18],"safely":[19],"in":[20,97,125],"complicated":[21],"scenarios.":[22],"In":[23],"multiagent":[24],"competitive":[25],"scenarios,":[26],"agents":[27],"may":[28],"have":[29],"adapt":[31],"new":[33],"opponents":[34],"with":[35,129,153],"previously":[36],"unseen":[37],"behaviors":[38],"by":[39],"learning":[40],"from":[41],"interaction":[43],"experiences":[44],"between":[45],"ego-agent":[47,61,100,150],"and":[48,112,154],"opponent.":[50],"However,":[51],"this":[52,83,89],"adaptation":[53,95,143],"susceptible":[55],"opponent":[57,106,147,161],"exploitation.":[58,162],"As":[59],"updates":[62],"its":[63,70],"own":[64,71],"behavior":[65,72],"exploit":[67],"opponent,":[69],"could":[73],"become":[74],"more":[75],"exploitable":[76],"as":[77],"result":[79],"overfitting":[81,111],"specific":[84,146],"opponent's":[85],"behavior.":[86],"To":[87],"overcome":[88],"difficulty,":[90],"we":[91],"developed":[92],"safe":[94],"approach":[96,124,139],"which":[98,108],"trained":[102],"against":[103],"regularized":[105],"model,":[107],"effectively":[109,140],"avoids":[110],"consequently":[113],"improves":[114],"robustness":[116],"ego-agent's":[119],"policy.":[120],"We":[121],"evaluated":[122],"our":[123,138],"Mujoco":[127],"domain":[128],"two":[130],"competing":[131],"agents.":[132],"The":[133],"experiment":[134],"results":[135],"suggest":[136],"achieves":[141],"both":[142],"interacting":[152],"maintaining":[155],"low":[156],"exploitability":[157],"other":[159],"possible":[160]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}