{"id":"https://openalex.org/W2918462111","doi":"https://doi.org/10.1145/3297156.3297217","title":"Continuous Control in Car Simulator with Deep Reinforcement Learning","display_name":"Continuous Control in Car Simulator with Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-12-08","ids":{"openalex":"https://openalex.org/W2918462111","doi":"https://doi.org/10.1145/3297156.3297217","mag":"2918462111"},"language":"en","primary_location":{"id":"doi:10.1145/3297156.3297217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297156.3297217","pdf_url":null,"source":{"id":"https://openalex.org/S4306523626","display_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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/A5060993812","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-8916-8605"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fan Yang","raw_affiliation_strings":["School of Electronics and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338672","display_name":"Ping Wang","orcid":"https://orcid.org/0000-0002-6917-6050"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Wang","raw_affiliation_strings":["School of Electronics and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100632520","display_name":"Xinhong Wang","orcid":"https://orcid.org/0000-0002-9704-4506"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XinHong Wang","raw_affiliation_strings":["School of Electronics and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060993812"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.077,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47796474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"566","last_page":"570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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":0.996999979019165,"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/T12810","display_name":"Real-time simulation and control systems","score":0.9958000183105469,"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":0.7579915523529053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6978430151939392},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.5167483687400818},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4690682590007782},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45638588070869446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35909876227378845},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15600717067718506},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05674314498901367}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7579915523529053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6978430151939392},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.5167483687400818},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4690682590007782},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45638588070869446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35909876227378845},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15600717067718506},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05674314498901367}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297156.3297217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297156.3297217","pdf_url":null,"source":{"id":"https://openalex.org/S4306523626","display_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W629297016","https://openalex.org/W1574474448","https://openalex.org/W2047030012","https://openalex.org/W2055207897","https://openalex.org/W2115579991","https://openalex.org/W2145339207","https://openalex.org/W2167224731","https://openalex.org/W2173248099","https://openalex.org/W2260756217","https://openalex.org/W2559767995","https://openalex.org/W2563338958","https://openalex.org/W2580175322","https://openalex.org/W2727840223","https://openalex.org/W2742454413","https://openalex.org/W2745868649","https://openalex.org/W2869375357","https://openalex.org/W2914316834","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3000146553","https://openalex.org/W3100789280"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Deep":[0,91],"reinforcement":[1],"learning":[2],"(DRL),":[3],"which":[4,102],"can":[5,29],"be":[6,30],"trained":[7],"without":[8],"abundant":[9],"labeled":[10],"data":[11],"required":[12],"in":[13,20,63,83,109],"supervised":[14],"learning,":[15],"plays":[16],"an":[17],"important":[18],"role":[19],"autonomous":[21],"vehicle":[22],"researches.":[23],"According":[24],"to":[25,53,71],"action":[26],"space,":[27],"DRL":[28],"further":[31],"divided":[32],"into":[33],"two":[34],"classes:":[35],"discrete":[36,57],"domain":[37],"and":[38,96],"continuous":[39,47,110],"domain.":[40,111],"In":[41],"this":[42],"work,":[43],"we":[44,78],"focus":[45],"on":[46,90],"steering":[48,58,69,120],"control":[49],"since":[50],"it's":[51],"impossible":[52],"switch":[54],"among":[55],"different":[56],"values":[59],"at":[60],"short":[61],"intervals":[62],"reality.":[64],"We":[65,86],"first":[66],"define":[67],"the":[68,73,104,107,115,119],"smoothness":[70,121],"quantify":[72],"degree":[74],"of":[75,106],"continuity.":[76],"Then":[77],"propose":[79],"a":[80],"new":[81],"penalty":[82,117],"reward":[84],"shaping.":[85],"carry":[87],"experiments":[88],"based":[89],"Deterministic":[92],"Policy":[93],"Gradient":[94],"(DDPG)":[95],"Asynchronous":[97],"Advantage":[98],"Actor":[99],"Critic":[100],"(A3C),":[101],"are":[103],"state":[105],"art":[108],"Results":[112],"show":[113],"that":[114],"proposed":[116],"improves":[118],"with":[122],"both":[123],"algorithms.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}