{"id":"https://openalex.org/W2962810885","doi":"https://doi.org/10.1109/icsess.2018.8663794","title":"Orthogonal Policy Gradient and Autonomous Driving Application","display_name":"Orthogonal Policy Gradient and Autonomous Driving Application","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2962810885","doi":"https://doi.org/10.1109/icsess.2018.8663794","mag":"2962810885"},"language":"en","primary_location":{"id":"doi:10.1109/icsess.2018.8663794","doi":"https://doi.org/10.1109/icsess.2018.8663794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsess.2018.8663794","pdf_url":null,"source":{"id":"https://openalex.org/S7407089132","display_name":"IEEE International Conference on Software Engineering and Service Science (ICSESS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.06151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060510208","display_name":"Mincong Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210096139","display_name":"China Institute of Atomic Energy","ror":"https://ror.org/00v5gqm66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210096139"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mincong Luo","raw_affiliation_strings":["Department of Information Centre, China Institute of Atomic Energy, Peking, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Centre, China Institute of Atomic Energy, Peking, China","institution_ids":["https://openalex.org/I4210096139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000643265","display_name":"Tong Yin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210096139","display_name":"China Institute of Atomic Energy","ror":"https://ror.org/00v5gqm66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210096139"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Tong","raw_affiliation_strings":["Department of Information Centre, China Institute of Atomic Energy, Peking, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Centre, China Institute of Atomic Energy, Peking, China","institution_ids":["https://openalex.org/I4210096139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019606204","display_name":"Jiachi Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210096139","display_name":"China Institute of Atomic Energy","ror":"https://ror.org/00v5gqm66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210096139"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachi Liu","raw_affiliation_strings":["Department of Information Centre, China Institute of Atomic Energy, Peking, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Centre, China Institute of Atomic Energy, Peking, China","institution_ids":["https://openalex.org/I4210096139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210096139"],"apc_list":null,"apc_paid":null,"fwci":0.1769,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.40933838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":9.999999747378752e-05,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8019999861717224},{"id":"https://openalex.org/keywords/model-generalization","display_name":"model generalization","score":0.7950000166893005},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.8500000238418579},{"id":"https://openalex.org/keywords/torcs","display_name":"TORCS","score":0.8870000243186951}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8337114453315735},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.809035062789917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498564720153809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6127060055732727},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5869247317314148},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5563899278640747},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5451521277427673},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.5292301177978516},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5185278654098511},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5067079663276672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39651697874069214},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30111876130104065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19203513860702515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12397953867912292},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07368281483650208},{"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/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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icsess.2018.8663794","doi":"https://doi.org/10.1109/icsess.2018.8663794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsess.2018.8663794","pdf_url":null,"source":{"id":"https://openalex.org/S7407089132","display_name":"IEEE International Conference on Software Engineering and Service Science (ICSESS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.06151","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06151","pdf_url":"https://arxiv.org/pdf/1811.06151","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1811.06151","doi":"https://doi.org/10.48550/arxiv.1811.06151","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.06151","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.06151","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06151","pdf_url":"https://arxiv.org/pdf/1811.06151","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962810885.pdf","grobid_xml":"https://content.openalex.org/works/W2962810885.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W2108714558","https://openalex.org/W2121615981","https://openalex.org/W2125612430","https://openalex.org/W2139137304","https://openalex.org/W2147750403","https://openalex.org/W2260756217","https://openalex.org/W2372555112","https://openalex.org/W2481567506","https://openalex.org/W2529573675","https://openalex.org/W2760485405"],"related_works":["https://openalex.org/W2902243259","https://openalex.org/W6959822703","https://openalex.org/W3016708448","https://openalex.org/W7093093898","https://openalex.org/W3207434759","https://openalex.org/W2530849036","https://openalex.org/W4411213468","https://openalex.org/W4393140561","https://openalex.org/W4413426027","https://openalex.org/W3206880326"],"abstract_inverted_index":{"One":[0],"less":[1],"addressed":[2],"issue":[3],"of":[4,11,123],"deep":[5,41],"reinforcement":[6,42],"learning":[7,43],"is":[8,25],"the":[9,29,52,61,80,85,89,94,106,110,118],"lack":[10],"generalization":[12,102],"capability":[13],"based":[14,59,83],"on":[15,60,84,109],"new":[16,19],"state":[17,87],"and":[18,32,55,88,126],"target,":[20],"for":[21,37],"complex":[22],"tasks,":[23],"it":[24],"necessary":[26],"to":[27],"give":[28],"correct":[30,53],"strategy":[31,54],"evaluate":[33,105],"all":[34,57],"possible":[35],"actions":[36,58,90],"current":[38,86],"state.":[39,62],"Fortunately,":[40],"has":[44],"enabled":[45],"enormous":[46],"progress":[47],"in":[48],"both":[49],"subproblems:":[50],"Giving":[51],"evaluating":[56],"In":[63],"this":[64],"paper":[65],"we":[66,104],"present":[67],"an":[68],"approach":[69],"called":[70],"orthogonal":[71],"policy":[72,81,99],"gradient":[73,82],"descent(OPGD)":[74],"that":[75],"can":[76,96],"make":[77],"agent":[78,95],"learn":[79,97],"set,":[91],"by":[92],"which":[93],"a":[98],"network":[100],"with":[101,117],"capability.":[103],"proposed":[107],"method":[108],"3D":[111],"autonomous":[112],"driving":[113],"enviroment":[114],"TORCS":[115],"compared":[116],"baseline":[119],"model,":[120],"detailed":[121],"analyses":[122],"experimental":[124],"results":[125],"proofs":[127],"are":[128],"also":[129],"given.":[130]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-30T00:00:00"}