{"id":"https://openalex.org/W4220805304","doi":"https://doi.org/10.3390/robotics11020035","title":"Research on Game-Playing Agents Based on Deep Reinforcement Learning","display_name":"Research on Game-Playing Agents Based on Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-03-18","ids":{"openalex":"https://openalex.org/W4220805304","doi":"https://doi.org/10.3390/robotics11020035"},"language":"en","primary_location":{"id":"doi:10.3390/robotics11020035","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics11020035","pdf_url":"https://www.mdpi.com/2218-6581/11/2/35/pdf?version=1647595383","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2218-6581/11/2/35/pdf?version=1647595383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057922575","display_name":"Kai Zhao","orcid":"https://orcid.org/0000-0002-2172-6607"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Zhao","raw_affiliation_strings":["School of Astronautics, Beihang University (BUAA), Beijing 100191, China"],"raw_orcid":"https://orcid.org/0000-0002-2172-6607","affiliations":[{"raw_affiliation_string":"School of Astronautics, Beihang University (BUAA), Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033366428","display_name":"Jia Song","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia Song","raw_affiliation_strings":["School of Astronautics, Beihang University (BUAA), Beijing 100191, China"],"raw_orcid":"https://orcid.org/0000-0002-4019-970X","affiliations":[{"raw_affiliation_string":"School of Astronautics, Beihang University (BUAA), Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056822347","display_name":"Yuxie Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxie Luo","raw_affiliation_strings":["School of Astronautics, Beihang University (BUAA), Beijing 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Astronautics, Beihang University (BUAA), Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033366428"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":2.081,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88573639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"11","issue":"2","first_page":"35","last_page":"35"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9828000068664551,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7957983016967773},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6705037951469421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6580467224121094},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5540440082550049},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5304087400436401},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5268845558166504},{"id":"https://openalex.org/keywords/interception","display_name":"Interception","score":0.46757274866104126},{"id":"https://openalex.org/keywords/evaluation-function","display_name":"Evaluation function","score":0.4613734483718872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4606277048587799},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4503435790538788},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.44698241353034973},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.329576313495636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07314479351043701}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7957983016967773},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6705037951469421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6580467224121094},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5540440082550049},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5304087400436401},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5268845558166504},{"id":"https://openalex.org/C61270487","wikidata":"https://www.wikidata.org/wiki/Q476843","display_name":"Interception","level":2,"score":0.46757274866104126},{"id":"https://openalex.org/C131806220","wikidata":"https://www.wikidata.org/wiki/Q852705","display_name":"Evaluation function","level":2,"score":0.4613734483718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4606277048587799},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4503435790538788},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.44698241353034973},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.329576313495636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07314479351043701},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/robotics11020035","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics11020035","pdf_url":"https://www.mdpi.com/2218-6581/11/2/35/pdf?version=1647595383","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c90f9f07cd624875a3beab906b239c2d","is_oa":true,"landing_page_url":"https://doaj.org/article/c90f9f07cd624875a3beab906b239c2d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics, Vol 11, Iss 2, p 35 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2218-6581/11/2/35/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/robotics11020035","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/robotics11020035","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics11020035","pdf_url":"https://www.mdpi.com/2218-6581/11/2/35/pdf?version=1647595383","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5883920160","display_name":null,"funder_award_id":"61473015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6726900636","display_name":null,"funder_award_id":"62073020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8896683101","display_name":null,"funder_award_id":"91646108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220805304.pdf","grobid_xml":"https://content.openalex.org/works/W4220805304.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2099618002","https://openalex.org/W2891816981","https://openalex.org/W2897661175","https://openalex.org/W2906436642","https://openalex.org/W2930863966","https://openalex.org/W2962917939","https://openalex.org/W2966633400","https://openalex.org/W2967847744","https://openalex.org/W3010604679","https://openalex.org/W3017041505","https://openalex.org/W3037033265","https://openalex.org/W3088197938","https://openalex.org/W3088314378","https://openalex.org/W3088521775","https://openalex.org/W3164923438","https://openalex.org/W4213377513","https://openalex.org/W6684205842","https://openalex.org/W6754954660","https://openalex.org/W6776362279"],"related_works":["https://openalex.org/W2359600231","https://openalex.org/W2380019117","https://openalex.org/W3138952546","https://openalex.org/W1987886368","https://openalex.org/W1660309994","https://openalex.org/W2369187583","https://openalex.org/W3197207153","https://openalex.org/W2127562195","https://openalex.org/W2382074051","https://openalex.org/W3027833737"],"abstract_inverted_index":{"Path":[0],"planning":[1,24],"is":[2,94],"a":[3],"key":[4],"technology":[5],"for":[6],"the":[7,29,35,45,50,59,64,74,83,88,92,98],"autonomous":[8],"mobility":[9],"of":[10],"intelligent":[11],"robots.":[12],"However,":[13],"there":[14],"are":[15],"few":[16],"studies":[17],"on":[18,34],"how":[19],"to":[20,57],"carry":[21],"out":[22],"path":[23],"in":[25,97],"real":[26],"time":[27],"under":[28],"confrontation":[30],"environment.":[31],"Therefore,":[32],"based":[33],"deep":[36],"deterministic":[37],"policy":[38],"gradient":[39],"(DDPG)":[40],"algorithm,":[41],"this":[42],"paper":[43],"designs":[44],"reward":[46,54],"function":[47],"and":[48,53,62,85],"adopts":[49],"incremental":[51],"training":[52,60],"compensation":[55],"method":[56],"improve":[58],"efficiency":[61],"obtain":[63],"penetration":[65],"strategy.":[66],"The":[67],"Monte":[68],"Carlo":[69],"experiment":[70],"results":[71],"show":[72],"that":[73],"algorithm":[75,93],"can":[76],"effectively":[77],"avoid":[78],"static":[79],"obstacles,":[80],"break":[81],"through":[82],"interception,":[84],"finally":[86],"reach":[87],"target":[89],"area.":[90],"Moreover,":[91],"also":[95],"validated":[96],"Webots":[99],"simulator.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}