{"id":"https://openalex.org/W2604765727","doi":"https://doi.org/10.1109/icra.2017.7989106","title":"Scalable accelerated decentralized multi-robot policy search in continuous observation spaces","display_name":"Scalable accelerated decentralized multi-robot policy search in continuous observation spaces","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2604765727","doi":"https://doi.org/10.1109/icra.2017.7989106","mag":"2604765727"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/114736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052169592","display_name":"Shayegan Omidshafiei","orcid":"https://orcid.org/0000-0001-7758-1454"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shayegan Omidshafiei","raw_affiliation_strings":["MIT, Laboratory for Information and Decision Systems (LIDS), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, Laboratory for Information and Decision Systems (LIDS), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033129735","display_name":"Christopher Amato","orcid":"https://orcid.org/0000-0002-6786-7384"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Amato","raw_affiliation_strings":["College of Computer and Information Science (CCIS), Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Science (CCIS), Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348892","display_name":"Miao Liu","orcid":"https://orcid.org/0009-0004-5086-7443"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Liu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064513857","display_name":"Michael Everett","orcid":"https://orcid.org/0000-0001-9377-6745"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Everett","raw_affiliation_strings":["MIT, Laboratory for Information and Decision Systems (LIDS), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, Laboratory for Information and Decision Systems (LIDS), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["MIT, Laboratory for Information and Decision Systems (LIDS), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, Laboratory for Information and Decision Systems (LIDS), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042445283","display_name":"John Vian","orcid":null},"institutions":[{"id":"https://openalex.org/I1295339012","display_name":"Boeing (United States)","ror":"https://ror.org/04sm5zn07","country_code":"US","type":"company","lineage":["https://openalex.org/I1295339012"]},{"id":"https://openalex.org/I4210115859","display_name":"Behavioral Tech Research, Inc.","ror":"https://ror.org/02843s885","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115859"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Vian","raw_affiliation_strings":["Boeing Research & Technology, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boeing Research & Technology, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210115859","https://openalex.org/I1295339012"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2197,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55869297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"31","issue":null,"first_page":"863","last_page":"870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9753000140190125,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.726554274559021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.711073637008667},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.648822546005249},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5847522020339966},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5292438864707947},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48612451553344727},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48441511392593384},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4628865420818329},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.42425405979156494},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42265334725379944},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3806885778903961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3391285538673401},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22349056601524353},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.21269014477729797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18282052874565125}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.726554274559021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711073637008667},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.648822546005249},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5847522020339966},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5292438864707947},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48612451553344727},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48441511392593384},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4628865420818329},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42425405979156494},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42265334725379944},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3806885778903961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3391285538673401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22349056601524353},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.21269014477729797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18282052874565125},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra.2017.7989106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/114736","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/114736","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/114736","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/114736","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W123090642","https://openalex.org/W145490631","https://openalex.org/W1493327649","https://openalex.org/W1564947197","https://openalex.org/W1565394148","https://openalex.org/W1670739992","https://openalex.org/W1886379263","https://openalex.org/W2025217226","https://openalex.org/W2043182541","https://openalex.org/W2087992130","https://openalex.org/W2088956500","https://openalex.org/W2095701584","https://openalex.org/W2103541323","https://openalex.org/W2133615895","https://openalex.org/W2144088174","https://openalex.org/W2162112538","https://openalex.org/W2408811396","https://openalex.org/W2747213132","https://openalex.org/W2978725006","https://openalex.org/W4240202985","https://openalex.org/W4242420607","https://openalex.org/W6604974139","https://openalex.org/W6633791246","https://openalex.org/W6661425395","https://openalex.org/W6675567943","https://openalex.org/W6681718981"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"This":[0,22,83],"paper":[1],"presents":[2],"the":[3,70,93],"first":[4,71],"ever":[5,72],"approach":[6,114],"for":[7,115],"solving":[8],"continuous-observation":[9,40,73],"Decentralized":[10],"Partially":[11],"Observable":[12],"Markov":[13],"Decision":[14],"Processes":[15],"(Dec-POMDPs)":[16],"and":[17,67,90,118,125],"their":[18,102],"semi-Markovian":[19],"counterparts,":[20],"Dec-POSMDPs.":[21],"contribution":[23],"is":[24,43,65,85,122],"especially":[25],"important":[26],"in":[27],"robotics,":[28],"where":[29,76],"a":[30],"vast":[31],"number":[32],"of":[33],"sensors":[34],"provide":[35],"continuous":[36,117],"observation":[37,120],"data.":[38],"A":[39],"policy":[41,111,133],"representation":[42],"introduced":[44,66],"using":[45,60],"Stochastic":[46],"Kernel-based":[47],"Finite":[48],"State":[49],"Automata":[50],"(SK-FSAs).":[51],"An":[52],"SK-FSA":[53],"search":[54,112],"algorithm":[55],"titled":[56],"Entropy-based":[57],"Policy":[58],"Search":[59],"Continuous":[61],"Kernel":[62],"Observations":[63],"(EPSCKO)":[64],"applied":[68],"to":[69,88,101,127],"Dec-POMDP/Dec-POSMDP":[74],"domain,":[75],"it":[77],"significantly":[78],"outperforms":[79],"state-of-the-art":[80],"discrete":[81,119],"approaches.":[82],"methodology":[84],"equally":[86],"applicable":[87],"Dec-POMDPs":[89],"Dec-POSMDPs,":[91],"though":[92],"empirical":[94],"analysis":[95],"presented":[96],"focuses":[97],"on":[98],"Dec-POSMDPs":[99],"due":[100],"higher":[103],"scalability.":[104],"To":[105],"improve":[106,128],"convergence,":[107],"an":[108],"entropy":[109],"injection":[110],"acceleration":[113],"both":[116],"cases":[121],"also":[123],"developed":[124],"shown":[126],"convergence":[129],"rates":[130],"without":[131],"degrading":[132],"quality.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}