{"id":"https://openalex.org/W4308939568","doi":"https://doi.org/10.5302/j.icros.2022.22.0145","title":"Deep Reinforcement Learning Based on the Hindsight Experience Replay for Autonomous Driving of Mobile Robot","display_name":"Deep Reinforcement Learning Based on the Hindsight Experience Replay for Autonomous Driving of Mobile Robot","publication_year":2022,"publication_date":"2022-11-11","ids":{"openalex":"https://openalex.org/W4308939568","doi":"https://doi.org/10.5302/j.icros.2022.22.0145"},"language":"en","primary_location":{"id":"doi:10.5302/j.icros.2022.22.0145","doi":"https://doi.org/10.5302/j.icros.2022.22.0145","is_oa":false,"landing_page_url":"https://doi.org/10.5302/j.icros.2022.22.0145","pdf_url":null,"source":{"id":"https://openalex.org/S4210183236","display_name":"Journal of Institute of Control Robotics and Systems","issn_l":"1976-5622","issn":["1976-5622","2233-4335"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["kci-registered","poland-40","russia-white-list-2"],"host_organization":"https://openalex.org/P4323366859","host_organization_name":"Institute of Control, Robotics and Systems","host_organization_lineage":["https://openalex.org/P4323366859"],"host_organization_lineage_names":["Institute of Control, Robotics and Systems"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Institute of Control, Robotics and Systems","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5101764872","display_name":"Minjae Park","orcid":"https://orcid.org/0000-0002-6664-4656","observed_orcids":["https://orcid.org/0000-0002-6664-4656"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minjae Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112877383","display_name":"Jin-Seok Hong","orcid":"https://orcid.org/0009-0008-4647-5016","observed_orcids":["https://orcid.org/0009-0008-4647-5016"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin-Seok Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030573764","display_name":"Nam-Kyu Kwon","orcid":"https://orcid.org/0000-0001-5342-8017","observed_orcids":["https://orcid.org/0000-0001-5342-8017"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nam-Kyu Kwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"28","issue":"11","first_page":"1006","last_page":"1012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hindsight-experience-replay","display_name":"hindsight experience replay","score":0.9210000038146973},{"id":"https://openalex.org/keywords/ddpg","display_name":"deep deterministic policy gradient","score":0.8659999966621399},{"id":"https://openalex.org/keywords/reward-engineering","display_name":"reward engineering","score":0.7900000214576721},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.7329999804496765},{"id":"https://openalex.org/keywords/mobile-robots","display_name":"mobile robots","score":0.6840000152587891},{"id":"https://openalex.org/keywords/turtlebot3","display_name":"TurtleBot3","score":0.9380000233650208},{"id":"https://openalex.org/keywords/gazebo-simulation","display_name":"Gazebo simulation","score":0.7829999923706055},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.7599999904632568}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.931524395942688},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8696296811103821},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.7943625450134277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730402946472168},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.627587080001831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5855622291564941},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5375527739524841},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.43250152468681335},{"id":"https://openalex.org/C2778835581","wikidata":"https://www.wikidata.org/wiki/Q2916098","display_name":"Autonomous robot","level":4,"score":0.4321483373641968},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.35298699140548706},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05153819918632507},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5302/j.icros.2022.22.0145","doi":"https://doi.org/10.5302/j.icros.2022.22.0145","is_oa":false,"landing_page_url":"https://doi.org/10.5302/j.icros.2022.22.0145","pdf_url":null,"source":{"id":"https://openalex.org/S4210183236","display_name":"Journal of Institute of Control Robotics and Systems","issn_l":"1976-5622","issn":["1976-5622","2233-4335"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["kci-registered","poland-40","russia-white-list-2"],"host_organization":"https://openalex.org/P4323366859","host_organization_name":"Institute of Control, Robotics and Systems","host_organization_lineage":["https://openalex.org/P4323366859"],"host_organization_lineage_names":["Institute of Control, Robotics and Systems"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Institute of Control, Robotics and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4311729143","https://openalex.org/W4390877994","https://openalex.org/W6959822703","https://openalex.org/W7166712371","https://openalex.org/W6922278269","https://openalex.org/W3116276448","https://openalex.org/W3006355000","https://openalex.org/W7102393154","https://openalex.org/W7004920847","https://openalex.org/W4225773281"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,74],"present":[4,75],"a":[5,21,53],"method":[6],"to":[7],"overcome":[8],"the":[9,17,26,40,50,59,68,71,76,80],"sparse":[10],"reward":[11,37],"problem":[12],"that":[13],"can":[14],"occur":[15],"in":[16,49],"autonomous":[18],"driving":[19],"of":[20,32,70,82],"mobile":[22,46],"robot":[23,47,54],"based":[24],"on":[25],"deep":[27],"deterministic":[28],"policy":[29],"gradient":[30],"algorithm":[31],"reinforcement":[33],"learning":[34],"using":[35,64],"simple":[36],"engineering":[38],"and":[39,58],"hindsight":[41],"experience":[42],"replay":[43],"technique.":[44],"The":[45],"used":[48],"experiment":[51],"is":[52],"operating":[55],"system-based":[56],"TurtleBot3,":[57],"experimental":[60,77],"environment":[61],"was":[62],"configured":[63],"Gazebo.":[65],"To":[66],"validate":[67],"effectiveness":[69],"proposed":[72],"technique,":[73],"results":[78],"with":[79],"application":[81],"HER.":[83]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2022-11-19T00:00:00"}