{"id":"https://openalex.org/W2586106701","doi":"https://doi.org/10.1109/devlrn.2016.7846790","title":"Emergence of communication among reinforcement learning agents under coordination environment","display_name":"Emergence of communication among reinforcement learning agents under coordination environment","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2586106701","doi":"https://doi.org/10.1109/devlrn.2016.7846790","mag":"2586106701"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2016.7846790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2016.7846790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","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/A5013879483","display_name":"Qiong Huang","orcid":"https://orcid.org/0000-0002-1958-6094"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Qiong Huang","raw_affiliation_strings":["Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan"],"affiliations":[{"raw_affiliation_string":"Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan","institution_ids":["https://openalex.org/I142637625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031054137","display_name":"Eiji Uchibe","orcid":"https://orcid.org/0000-0001-7908-0258"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eiji Uchibe","raw_affiliation_strings":["Dept. of Brain Robot Interface, ATR Computational Neuroscience Labs, Kyoto, Japan","Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan"],"affiliations":[{"raw_affiliation_string":"Dept. of Brain Robot Interface, ATR Computational Neuroscience Labs, Kyoto, Japan","institution_ids":[]},{"raw_affiliation_string":"Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan","institution_ids":["https://openalex.org/I142637625"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004840638","display_name":"Kenji Doya","orcid":"https://orcid.org/0000-0002-2446-6820"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Doya","raw_affiliation_strings":["Gakko Hojin Okinawa Kagaku Gijutsu Daigakuin Daigaku Gakuen, Kunigami-gun, Okinawa, JP"],"affiliations":[{"raw_affiliation_string":"Gakko Hojin Okinawa Kagaku Gijutsu Daigakuin Daigaku Gakuen, Kunigami-gun, Okinawa, JP","institution_ids":["https://openalex.org/I142637625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013879483"],"corresponding_institution_ids":["https://openalex.org/I142637625"],"apc_list":null,"apc_paid":null,"fwci":1.2854,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87854507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9973000288009644,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9786999821662903,"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/observability","display_name":"Observability","score":0.9114593267440796},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9094696044921875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7428418397903442},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.7214277982711792},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6604395508766174},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.545342206954956},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5085667371749878},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4547445476055145},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4141651391983032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41229304671287537},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33038491010665894},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11115676164627075},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0747571587562561}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9114593267440796},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9094696044921875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428418397903442},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7214277982711792},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6604395508766174},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.545342206954956},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5085667371749878},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4547445476055145},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4141651391983032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41229304671287537},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33038491010665894},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11115676164627075},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0747571587562561},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2016.7846790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2016.7846790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2013903324","https://openalex.org/W2042273730","https://openalex.org/W2395575420","https://openalex.org/W2396345291","https://openalex.org/W2402402867","https://openalex.org/W2964338167","https://openalex.org/W6712181171","https://openalex.org/W6712549828","https://openalex.org/W6713411898"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3029572990"],"abstract_inverted_index":{"We":[0,22,45],"have":[1],"proposed":[2],"a":[3,12,37,42,48],"way":[4,50],"to":[5,40,51],"simulate":[6],"how":[7],"communication":[8,29],"could":[9,35],"emerge":[10],"in":[11,61],"simple":[13,27],"n":[14,16],"by":[15,25],"grid":[17],"world":[18],"task":[19],"among":[20,30],"multi-agent.":[21],"showed":[23],"that":[24],"introducing":[26],"learning":[28,60],"multi":[31],"reinforcement":[32,59],"learners,":[33],"agents":[34],"reach":[36],"coordinated":[38],"behavior":[39],"obtain":[41],"higher":[43],"reward.":[44],"also":[46],"provided":[47],"feasible":[49],"overcome":[52],"the":[53],"problem":[54],"of":[55],"partial":[56],"observability":[57],"with":[58],"multi-agent":[62],"systems.":[63]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}