{"id":"https://openalex.org/W2127637506","doi":"https://doi.org/10.1109/iros.2009.5354406","title":"Cooperative multi-robot reinforcement learning: A framework in hybrid state space","display_name":"Cooperative multi-robot reinforcement learning: A framework in hybrid state space","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2127637506","doi":"https://doi.org/10.1109/iros.2009.5354406","mag":"2127637506"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2009.5354406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2009.5354406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5100973144","display_name":"Xueqing Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xueqing Sun","raw_affiliation_strings":["Thayer School of Engineering, Dartmouth College, Hanover, NH, USA","Thayer School of Engineering, Dartmouth College Hanover NH 03755 USA"],"affiliations":[{"raw_affiliation_string":"Thayer School of Engineering, Dartmouth College, Hanover, NH, USA","institution_ids":["https://openalex.org/I107672454"]},{"raw_affiliation_string":"Thayer School of Engineering, Dartmouth College Hanover NH 03755 USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034444844","display_name":"Tao Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Mao","raw_affiliation_strings":["Thayer School of Engineering, Dartmouth College, Hanover, NH, USA","Thayer School of Engineering, Dartmouth College Hanover NH 03755 USA"],"affiliations":[{"raw_affiliation_string":"Thayer School of Engineering, Dartmouth College, Hanover, NH, USA","institution_ids":["https://openalex.org/I107672454"]},{"raw_affiliation_string":"Thayer School of Engineering, Dartmouth College Hanover NH 03755 USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005748583","display_name":"Jerald D. Kralik","orcid":"https://orcid.org/0000-0001-7458-8001"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerald D. Kralik","raw_affiliation_strings":["Department of Psychological & Brain Sciences, Dartmouth College, Hanover, NH, USA","Department of Psychological and Brain Sciences, Dartmouth College, Hanover, NH, 03755, USA"],"affiliations":[{"raw_affiliation_string":"Department of Psychological & Brain Sciences, Dartmouth College, Hanover, NH, USA","institution_ids":["https://openalex.org/I107672454"]},{"raw_affiliation_string":"Department of Psychological and Brain Sciences, Dartmouth College, Hanover, NH, 03755, USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000034078","display_name":"Laura Ray","orcid":"https://orcid.org/0000-0001-7769-2373"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura E. Ray","raw_affiliation_strings":["Thayer School of Engineering, Dartmouth College, Hanover, NH, USA","Thayer School of Engineering, Dartmouth College Hanover NH 03755 USA"],"affiliations":[{"raw_affiliation_string":"Thayer School of Engineering, Dartmouth College, Hanover, NH, USA","institution_ids":["https://openalex.org/I107672454"]},{"raw_affiliation_string":"Thayer School of Engineering, Dartmouth College Hanover NH 03755 USA","institution_ids":["https://openalex.org/I107672454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100973144"],"corresponding_institution_ids":["https://openalex.org/I107672454"],"apc_list":null,"apc_paid":null,"fwci":2.6171,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90940239,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"8","issue":null,"first_page":"1190","last_page":"1196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9952999949455261,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8622527122497559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7560950517654419},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6687157154083252},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6621142625808716},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5847047567367554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5166680812835693},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4764150381088257},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41888725757598877},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.41862866282463074},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3599475026130676},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10807403922080994}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8622527122497559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560950517654419},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6687157154083252},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6621142625808716},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5847047567367554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5166680812835693},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4764150381088257},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41888725757598877},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.41862866282463074},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3599475026130676},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10807403922080994},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2009.5354406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2009.5354406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W42384017","https://openalex.org/W105052346","https://openalex.org/W827683006","https://openalex.org/W1507591516","https://openalex.org/W1513468570","https://openalex.org/W1515851193","https://openalex.org/W1542941925","https://openalex.org/W1547191063","https://openalex.org/W1557517019","https://openalex.org/W1586180972","https://openalex.org/W1593916827","https://openalex.org/W2012905391","https://openalex.org/W2014824949","https://openalex.org/W2104040810","https://openalex.org/W2104602264","https://openalex.org/W2107726111","https://openalex.org/W2108262002","https://openalex.org/W2128643385","https://openalex.org/W2137602277","https://openalex.org/W2142494410","https://openalex.org/W2147750403","https://openalex.org/W2148496763","https://openalex.org/W2153675913","https://openalex.org/W2165131254","https://openalex.org/W2167261463","https://openalex.org/W2172968643","https://openalex.org/W2399016715","https://openalex.org/W2500333127","https://openalex.org/W2752885492","https://openalex.org/W2799061466","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3011120880","https://openalex.org/W3145128584","https://openalex.org/W4230375458","https://openalex.org/W4233696721","https://openalex.org/W4254092108","https://openalex.org/W4301630257","https://openalex.org/W6601718342","https://openalex.org/W6604309264","https://openalex.org/W6630520071","https://openalex.org/W6633051906","https://openalex.org/W6653651359","https://openalex.org/W6675415372","https://openalex.org/W6675811377","https://openalex.org/W6681553090"],"related_works":["https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2579634771"],"abstract_inverted_index":{"In":[0],"the":[1,50,125],"area":[2],"of":[3,49,124,132],"autonomous":[4],"multi-robot":[5,39],"cooperation,":[6],"much":[7],"emphasis":[8],"has":[9],"been":[10],"placed":[11],"on":[12,43],"how":[13],"to":[14,21,26,37,52,88,90,99,112],"coordinate":[15],"individual":[16],"robot":[17],"behaviors":[18],"in":[19,61,104],"order":[20],"achieve":[22,53],"an":[23,35],"optimal":[24,120],"solution":[25,111],"task":[27,55],"completion":[28],"as":[29],"a":[30,44,62,73,78,109,118,133],"team.":[31],"This":[32],"paper":[33],"presents":[34],"approach":[36,97],"cooperative":[38],"reinforcement":[40],"learning":[41,56,69],"based":[42],"hybrid":[45],"state":[46],"space":[47,70],"representation":[48],"environment":[51],"both":[54],"and":[57,77,86,93,107],"heterogeneous":[58],"role":[59],"emergence":[60],"unified":[63],"framework.":[64],"The":[65,96],"methodology":[66],"also":[67],"involves":[68],"reduction":[71],"through":[72,130],"neural":[74],"perception":[75],"module":[76],"progressive":[79],"rescheduling":[80],"algorithm":[81],"that":[82],"interleaves":[83],"online":[84],"execution":[85],"relearning":[87],"adapt":[89],"environmental":[91],"uncertainties":[92],"enhance":[94],"performance.":[95],"aims":[98],"reduce":[100],"combinatorial":[101],"complexity":[102],"inherent":[103],"role-task":[105],"optimization,":[106],"achieves":[108],"satisfying":[110],"complex":[113],"team-based":[114],"tasks,":[115],"rather":[116],"than":[117],"globally":[119],"solution.":[121],"Empirical":[122],"evaluation":[123],"proposed":[126],"framework":[127],"is":[128],"conducted":[129],"simulation":[131],"foraging":[134],"task.":[135]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}