{"id":"https://openalex.org/W4383108785","doi":"https://doi.org/10.1109/icra48891.2023.10160947","title":"Show me What you want: Inverse Reinforcement Learning to Automatically Design Robot Swarms by Demonstration","display_name":"Show me What you want: Inverse Reinforcement Learning to Automatically Design Robot Swarms by Demonstration","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108785","doi":"https://doi.org/10.1109/icra48891.2023.10160947"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 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/A5076753239","display_name":"Ilyes Gharbi","orcid":null},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Ilyes Gharbi","raw_affiliation_strings":["Universit&#x00E9; libre de Bruxelles,IRIDIA,Brussels,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; libre de Bruxelles,IRIDIA,Brussels,Belgium","institution_ids":["https://openalex.org/I132053463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021453451","display_name":"Jonas Kuckling","orcid":"https://orcid.org/0000-0003-2391-2275"},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]},{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["BE","DE"],"is_corresponding":false,"raw_author_name":"Jonas Kuckling","raw_affiliation_strings":["Universit&#x00E9; libre de Bruxelles,IRIDIA,Brussels,Belgium","Department of Computer and Information Science, University of Konstanz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; libre de Bruxelles,IRIDIA,Brussels,Belgium","institution_ids":["https://openalex.org/I132053463"]},{"raw_affiliation_string":"Department of Computer and Information Science, University of Konstanz, Germany","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034691018","display_name":"David Garz\u00f3n Ramos","orcid":"https://orcid.org/0000-0001-7099-4213"},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"David Garz\u00f3n Ramos","raw_affiliation_strings":["Universit&#x00E9; libre de Bruxelles,IRIDIA,Brussels,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; libre de Bruxelles,IRIDIA,Brussels,Belgium","institution_ids":["https://openalex.org/I132053463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061782786","display_name":"Mauro Birattari","orcid":"https://orcid.org/0000-0003-3309-2194"},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Mauro Birattari","raw_affiliation_strings":["Universit&#x00E9; libre de Bruxelles,IRIDIA,Brussels,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; libre de Bruxelles,IRIDIA,Brussels,Belgium","institution_ids":["https://openalex.org/I132053463"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076753239"],"corresponding_institution_ids":["https://openalex.org/I132053463"],"apc_list":null,"apc_paid":null,"fwci":1.5107,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79820344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5063","last_page":"5070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965000152587891,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/modular-design","display_name":"Modular design","score":0.7094545364379883},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7055544853210449},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7051247358322144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6854958534240723},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.643055260181427},{"id":"https://openalex.org/keywords/software-design","display_name":"Software design","score":0.5254872441291809},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4698340594768524},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4290919899940491},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4249507188796997},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4083242416381836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40079402923583984},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3507038950920105},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.33849042654037476},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.2432967722415924},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17616018652915955},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1324215829372406}],"concepts":[{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7094545364379883},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7055544853210449},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7051247358322144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6854958534240723},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.643055260181427},{"id":"https://openalex.org/C52913732","wikidata":"https://www.wikidata.org/wiki/Q857102","display_name":"Software design","level":4,"score":0.5254872441291809},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4698340594768524},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4290919899940491},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4249507188796997},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4083242416381836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40079402923583984},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3507038950920105},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.33849042654037476},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2432967722415924},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17616018652915955},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1324215829372406},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1640319213","display_name":"Automatic Design of Robot Swarms","funder_award_id":"681872","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W760007050","https://openalex.org/W1524470902","https://openalex.org/W1997488333","https://openalex.org/W1999874108","https://openalex.org/W2008056655","https://openalex.org/W2011995167","https://openalex.org/W2017150251","https://openalex.org/W2030775133","https://openalex.org/W2031571562","https://openalex.org/W2062223562","https://openalex.org/W2070727087","https://openalex.org/W2102426751","https://openalex.org/W2107726111","https://openalex.org/W2116409257","https://openalex.org/W2117927893","https://openalex.org/W2118331730","https://openalex.org/W2124394479","https://openalex.org/W2131888821","https://openalex.org/W2149469814","https://openalex.org/W2170267824","https://openalex.org/W2170389705","https://openalex.org/W2202743478","https://openalex.org/W2270784458","https://openalex.org/W2274806495","https://openalex.org/W2301883550","https://openalex.org/W2402625038","https://openalex.org/W2473718451","https://openalex.org/W2757803868","https://openalex.org/W2760361646","https://openalex.org/W2787690100","https://openalex.org/W2790892475","https://openalex.org/W2883140436","https://openalex.org/W2884476204","https://openalex.org/W2886974401","https://openalex.org/W2905359332","https://openalex.org/W2923870875","https://openalex.org/W2924849247","https://openalex.org/W2978360819","https://openalex.org/W3014630000","https://openalex.org/W3048011184","https://openalex.org/W3098797556","https://openalex.org/W3099092915","https://openalex.org/W3111019671","https://openalex.org/W3176202740","https://openalex.org/W3178918501","https://openalex.org/W4211139152","https://openalex.org/W4253646082","https://openalex.org/W6674884181","https://openalex.org/W6689856497","https://openalex.org/W6753207554"],"related_works":["https://openalex.org/W2762381663","https://openalex.org/W1886477626","https://openalex.org/W4385196987","https://openalex.org/W1540467731","https://openalex.org/W218732962","https://openalex.org/W2538037439","https://openalex.org/W4317826762","https://openalex.org/W2741909783","https://openalex.org/W1979383880","https://openalex.org/W3110580084"],"abstract_inverted_index":{"Automatic":[0],"design":[1,16,49,59],"is":[2],"a":[3],"promising":[4],"approach":[5],"to":[6,23,36,79,92],"generating":[7],"control":[8,61,90],"software":[9,62,91],"for":[10,63],"robot":[11,64],"swarms.":[12,65],"So":[13],"far,":[14],"automatic":[15,48,57],"has":[17],"relied":[18],"on":[19,70],"mission-specific":[20],"objective":[21,85],"functions":[22],"specify":[24,37],"the":[25,34,38,71,77],"desired":[26,39],"collective":[27,40],"behavior.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"explore":[33],"possibility":[35],"behavior":[41],"via":[42],"demonstrations.":[43],"We":[44,66,96],"develop":[45],"Demo-Cho,":[46],"an":[47,83],"method":[50],"that":[51],"combines":[52],"inverse":[53],"reinforcement":[54],"learning":[55],"with":[56,82,103],"modular":[58],"of":[60,73],"show":[67],"that,":[68],"only":[69],"basis":[72],"demonstrations":[74],"and":[75,102],"without":[76],"need":[78],"be":[80],"provided":[81],"explicit":[84],"function,":[86],"Demo-Cho":[87],"successfully":[88],"generated":[89],"perform":[93],"four":[94],"missions.":[95],"present":[97],"results":[98],"obtained":[99],"in":[100],"simulation":[101],"physical":[104],"robots.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}
