{"id":"https://openalex.org/W2967762122","doi":"https://doi.org/10.1109/icra.2019.8794389","title":"Active Perception in Adversarial Scenarios using Maximum Entropy Deep Reinforcement Learning","display_name":"Active Perception in Adversarial Scenarios using Maximum Entropy Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2967762122","doi":"https://doi.org/10.1109/icra.2019.8794389","mag":"2967762122"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","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":["Department of Mechanical Engineering, Massachusetts Institute of Technology (MIT), 77 Massachusetts Ave., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Massachusetts Institute of Technology (MIT), 77 Massachusetts Ave., Cambridge, MA, USA","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/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":["Department of Aeronautics and Astronautics, MIT, 77 Massachusetts Ave., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, MIT, 77 Massachusetts Ave., Cambridge, MA, USA","institution_ids":["https://openalex.org/I46020346"]}]}],"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":1.1201,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83815538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3384","last_page":"3390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9987999796867371,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9909999966621399,"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/adversarial-system","display_name":"Adversarial system","score":0.8536022305488586},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8396860957145691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6709901094436646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6420443654060364},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5855490565299988},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5332427024841309},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5118740797042847},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5090996623039246},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3860968351364136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3229775130748749},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12982243299484253},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.09319636225700378},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07999229431152344}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8536022305488586},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8396860957145691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6709901094436646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6420443654060364},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5855490565299988},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5332427024841309},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5118740797042847},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5090996623039246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3860968351364136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3229775130748749},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12982243299484253},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.09319636225700378},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07999229431152344},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2019.8794389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W14769209","https://openalex.org/W206679605","https://openalex.org/W602128623","https://openalex.org/W1757796397","https://openalex.org/W1969351254","https://openalex.org/W2103315867","https://openalex.org/W2103976209","https://openalex.org/W2121092017","https://openalex.org/W2144274908","https://openalex.org/W2168839459","https://openalex.org/W2291986326","https://openalex.org/W2475089067","https://openalex.org/W2502437829","https://openalex.org/W2571676842","https://openalex.org/W2572445540","https://openalex.org/W2592798481","https://openalex.org/W2594103415","https://openalex.org/W2604283518","https://openalex.org/W2611623000","https://openalex.org/W2760963510","https://openalex.org/W2766447205","https://openalex.org/W2766768413","https://openalex.org/W2949201811","https://openalex.org/W2949561945","https://openalex.org/W2962893898","https://openalex.org/W2962938178","https://openalex.org/W2962941327","https://openalex.org/W2963067607","https://openalex.org/W2963407617","https://openalex.org/W2964164283","https://openalex.org/W3004707083","https://openalex.org/W4297573592","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W4300686497","https://openalex.org/W6600604141","https://openalex.org/W6618455370","https://openalex.org/W6637967152","https://openalex.org/W6675022307","https://openalex.org/W6675509861","https://openalex.org/W6677939520","https://openalex.org/W6681187623","https://openalex.org/W6684985892","https://openalex.org/W6696772115","https://openalex.org/W6721101288","https://openalex.org/W6734517396","https://openalex.org/W6734678876","https://openalex.org/W6735030908","https://openalex.org/W6736622323","https://openalex.org/W6738796088","https://openalex.org/W6742007199","https://openalex.org/W6745630456"],"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/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":{"We":[0,85],"pose":[1],"an":[2,7,64,87,145],"active":[3],"perception":[4],"problem":[5],"where":[6],"autonomous":[8,72,125,153],"agent":[9,15,52,66,73],"actively":[10],"interacts":[11],"with":[12,16,158],"a":[13,76,104,159],"second":[14],"potentially":[17],"adversarial":[18,113,136],"behaviors.":[19],"Given":[20],"the":[21,24,27,30,47,51,54,58,71,116,121,124,128,152],"uncertainty":[22,60],"in":[23,115],"intent":[25],"of":[26,50,123],"other":[28],"agent,":[29],"objective":[31],"is":[32,80,131,141],"to":[33,37,69,102,134,149],"collect":[34],"further":[35],"evidence":[36],"help":[38],"discriminate":[39],"potential":[40],"threats.":[41],"The":[42],"main":[43],"technical":[44],"challenges":[45],"are":[46],"partial":[48],"observability":[49],"intent,":[53],"adversary":[55,65,95,146],"modeling,":[56,96],"and":[57,97,119,150],"corresponding":[59],"modeling.":[61],"Note":[62],"that":[63,79,89,147],"may":[67],"act":[68],"mislead":[70],"by":[74],"using":[75],"deceptive":[77],"strategy":[78],"learned":[81],"from":[82],"past":[83],"experiences.":[84],"propose":[86],"approach":[88],"combines":[90],"belief":[91,106],"space":[92,107],"planning,":[93],"generative":[94],"maximum":[98],"entropy":[99],"reinforcement":[100],"learning":[101],"obtain":[103],"stochastic":[105],"policy.":[108],"By":[109],"accounting":[110],"for":[111],"various":[112],"behaviors":[114],"simulation":[117],"framework":[118],"minimizing":[120],"predictability":[122],"agent's":[126,154],"action,":[127],"resulting":[129],"policy":[130,155],"more":[132],"robust":[133,167],"unmodeled":[135],"strategies.":[137],"This":[138],"improved":[139],"robustness":[140],"empirically":[142],"shown":[143],"against":[144],"adapts":[148],"exploits":[151],"when":[156],"compared":[157],"standard":[160],"Chance-Constraint":[161],"Partially":[162],"Observable":[163],"Markov":[164],"Decision":[165],"Process":[166],"approach.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}