{"id":"https://openalex.org/W2897432694","doi":"https://doi.org/10.1109/ijcnn.2018.8489372","title":"Guided Deep Reinforcement Learning in the GeoFriends2 Environment","display_name":"Guided Deep Reinforcement Learning in the GeoFriends2 Environment","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2897432694","doi":"https://doi.org/10.1109/ijcnn.2018.8489372","mag":"2897432694"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081040128","display_name":"David Sim\u00f5es","orcid":"https://orcid.org/0000-0002-6464-8012"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Simoes","raw_affiliation_strings":["LIACC - Artificial Intelligence and Computer Science Lab, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIACC - Artificial Intelligence and Computer Science Lab, Porto, Portugal","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055569781","display_name":"Nuno Lau","orcid":"https://orcid.org/0000-0003-0513-158X"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Lau","raw_affiliation_strings":["DETI/UA - Electronics, University of Aveiro, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DETI/UA - Electronics, University of Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089812166","display_name":"Lu\u00eds Paulo Reis","orcid":"https://orcid.org/0000-0002-4709-1718"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Luis Paulo Reis","raw_affiliation_strings":["DEI/FEUP - Informatics Engineering Department, Faculty of Engineering of the University of Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEI/FEUP - Informatics Engineering Department, Faculty of Engineering of the University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 1605 2688","issue":null,"first_page":"1","last_page":"7"},"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":0.9965000152587891,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9897000193595886,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9172356128692627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8107945919036865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6642296314239502},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6146280169487},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6032555103302002},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5859614014625549},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5795807242393494},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48394325375556946},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47287461161613464},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4399985373020172},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4135458469390869},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4132990837097168},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.13808521628379822},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.09734338521957397}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9172356128692627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107945919036865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6642296314239502},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6146280169487},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6032555103302002},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5859614014625549},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5795807242393494},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48394325375556946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47287461161613464},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4399985373020172},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4135458469390869},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4132990837097168},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.13808521628379822},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.09734338521957397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1917426767","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2257979135","https://openalex.org/W2384495648","https://openalex.org/W2592076308","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2780635050","https://openalex.org/W2787259794","https://openalex.org/W2951799221","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"In":[0,121],"recent":[1],"years,":[2],"the":[3,12,57,76,80,103,108,111,141,144,192],"artificial":[4],"intelligence":[5],"community":[6],"has":[7],"taken":[8],"big":[9],"strides":[10],"in":[11,66,72,79,95,204],"application":[13],"of":[14,56,68,110,146,187],"reinforcement":[15,159],"learning":[16,39,48,104,112,193],"to":[17,27,49,74,91,167],"games":[18],"or":[19,33],"similar":[20],"environments":[21,105],"using":[22,210],"deep":[23,38],"learning.":[24,160],"From":[25],"Atari":[26],"board":[28],"games,":[29],"including":[30],"motor":[31],"control":[32],"riddle":[34],"solving,":[35],"fairly":[36],"generic":[37],"algorithms":[40,62,87],"can":[41,106,172,198],"now":[42],"achieve":[43,75,92],"great":[44],"policies":[45,170],"by":[46],"simply":[47],"play":[50],"from":[51],"experience,":[52],"and":[53,70,130,149,157,206,209],"minimal":[54],"knowledge":[55],"specific":[58],"domain.":[59],"However,":[60],"these":[61],"are":[63],"very":[64],"demanding":[65],"terms":[67],"time":[69],"hardware":[71,203],"order":[73],"results":[77],"reported":[78],"literature.":[81],"So":[82],"much":[83,211],"so,":[84],"that":[85,171,189,196],"some":[86],"would":[88],"take":[89],"years":[90],"state-of-the-art":[93],"performance":[94,119],"commodity":[96,202],"hardware.":[97],"Not":[98],"only":[99],"that,":[100],"but":[101],"even":[102],"hinder":[107],"speed":[109,190],"process,":[113],"if":[114],"they":[115],"have":[116],"not":[117,207],"been":[118],"optimized.":[120],"this":[122,180],"paper,":[123],"we":[124,136],"evaluate":[125],"a":[126,132,185],"complex":[127,169],"existing":[128],"environment,":[129],"propose":[131],"performance-oriented":[133],"version,":[134,148],"which":[135],"call":[137],"GeoFriends2.":[138],"We":[139,161,182],"describe":[140,184],"motivation":[142],"behind":[143],"creation":[145],"our":[147],"how":[150],"it":[151],"is":[152],"suitable":[153],"for":[154,176],"both":[155],"single-":[156],"multi-agent":[158],"then":[162],"use":[163],"Asynchronous":[164],"Deep":[165],"Learning":[166],"create":[168],"act":[173],"as":[174],"baselines":[175],"future":[177],"research":[178],"on":[179],"environment.":[181],"also":[183],"set":[186],"techniques":[188],"up":[191],"process":[194],"such":[195],"tests":[197],"be":[199],"run":[200],"with":[201],"hours,":[205],"weeks,":[208],"simpler":[212],"network":[213],"architectures.":[214]},"counts_by_year":[{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}