{"id":"https://openalex.org/W3133944220","doi":"https://doi.org/10.1109/iceic51217.2021.9369800","title":"Comparison of deep reinforcement learning algorithms: Path Search in Grid World","display_name":"Comparison of deep reinforcement learning algorithms: Path Search in Grid World","publication_year":2021,"publication_date":"2021-01-31","ids":{"openalex":"https://openalex.org/W3133944220","doi":"https://doi.org/10.1109/iceic51217.2021.9369800","mag":"3133944220"},"language":"en","primary_location":{"id":"doi:10.1109/iceic51217.2021.9369800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic51217.2021.9369800","pdf_url":null,"source":{"id":"https://openalex.org/S4306498844","display_name":"2021 International Conference on Electronics, Information, and Communication (ICEIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Electronics, Information, and Communication (ICEIC)","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/A5083813909","display_name":"Yungmin Sunwoo","orcid":null},"institutions":[{"id":"https://openalex.org/I8991828","display_name":"Pukyong National University","ror":"https://ror.org/0433kqc49","country_code":"KR","type":"education","lineage":["https://openalex.org/I8991828"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"YungMin SunWoo","raw_affiliation_strings":["Smart Robot Convergence and Application Engineering, Pukyong National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Smart Robot Convergence and Application Engineering, Pukyong National University, Republic of Korea","institution_ids":["https://openalex.org/I8991828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033964369","display_name":"Won\u2010Chang Lee","orcid":"https://orcid.org/0000-0001-7163-5183"},"institutions":[{"id":"https://openalex.org/I8991828","display_name":"Pukyong National University","ror":"https://ror.org/0433kqc49","country_code":"KR","type":"education","lineage":["https://openalex.org/I8991828"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"WonChang Lee","raw_affiliation_strings":["Smart Robot Convergence and Application Engineering, Pukyong National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Smart Robot Convergence and Application Engineering, Pukyong National University, Republic of Korea","institution_ids":["https://openalex.org/I8991828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083813909"],"corresponding_institution_ids":["https://openalex.org/I8991828"],"apc_list":null,"apc_paid":null,"fwci":0.1257,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29893438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"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":0.996999979019165,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.917109489440918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7112593650817871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6944352388381958},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6521573066711426},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6302109956741333},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6056084036827087},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5476074814796448},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5389336943626404},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.478903204202652},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4384411871433258},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.433030366897583},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4315986931324005},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.41220730543136597},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3353423476219177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10043150186538696}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.917109489440918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7112593650817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6944352388381958},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6521573066711426},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6302109956741333},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6056084036827087},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5476074814796448},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5389336943626404},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.478903204202652},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4384411871433258},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.433030366897583},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4315986931324005},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.41220730543136597},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3353423476219177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10043150186538696},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic51217.2021.9369800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic51217.2021.9369800","pdf_url":null,"source":{"id":"https://openalex.org/S4306498844","display_name":"2021 International Conference on Electronics, Information, and Communication (ICEIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Electronics, Information, and Communication (ICEIC)","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":7,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1757796397","https://openalex.org/W1977655452","https://openalex.org/W2121863487","https://openalex.org/W2173248099","https://openalex.org/W2963864421","https://openalex.org/W4298857966"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2930863966","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W2126211886","https://openalex.org/W1528400370"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,37,133,147],"learning":[2,38,59,134,148],"is":[3,27,72,87,101,154],"being":[4],"used":[5,171],"to":[6,31,41,77,81,97,104,112],"teach":[7],"robots":[8],"elaborate":[9],"and":[10,13,44,47,53,92,119,121,163,169],"complex":[11],"tasks,":[12],"recently,":[14],"it":[15],"has":[16],"gained":[17],"successful":[18],"results":[19,143],"in":[20,50,66,172],"various":[21,145],"fields":[22],"of":[23,56,63,117,144],"robotics.":[24],"However,":[25],"there":[26,86],"still":[28],"a":[29,54,75,90,93,102,155,160],"limit":[30],"directly":[32],"applying":[33],"the":[34,42,51,64,68,79,83,98,106,115,123,127,141,165,173],"existing":[35],"deep":[36,132,146],"algorithms":[39,149],"due":[40],"continuous":[43],"high-dimensional":[45],"states":[46],"actions":[48],"inherent":[49],"robot,":[52],"method":[55],"inducing":[57],"correct":[58],"through":[60,89],"proper":[61],"expression":[62],"environment":[65],"which":[67,153],"robot":[69,80],"will":[70],"work":[71,84,107],"required.":[73],"As":[74],"way":[76,103],"enable":[78],"recognize":[82],"environment,":[85,166],"observation":[88],"camera,":[91],"mapping":[94],"from":[95],"this":[96,137],"grid":[99,161],"world":[100],"express":[105],"environment.":[108],"This":[109],"allows":[110],"us":[111],"considerably":[113],"reduce":[114],"dimensions":[116],"state":[118],"action":[120],"find":[122],"optimal":[124],"policy":[125],"for":[126,150],"path":[128,151],"search":[129],"problem":[130,157],"using":[131],"algorithms.":[135],"In":[136],"paper,":[138],"we":[139],"compare":[140],"simulation":[142],"search,":[152],"representative":[156],"depicted":[158],"as":[159],"world,":[162],"present":[164],"model":[167],"architecture":[168],"parameters":[170],"simulation.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}