{"id":"https://openalex.org/W1562264016","doi":null,"title":"Reinforcement Learning for Racecar Control","display_name":"Reinforcement Learning for Racecar Control","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W1562264016","mag":"1562264016"},"language":"en","primary_location":{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/2507","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10289/2507","pdf_url":"https://hdl.handle.net/10289/2507","source":{"id":"https://openalex.org/S4306400944","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I52179390","host_organization_name":"University of Waikato","host_organization_lineage":["https://openalex.org/I52179390"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/10289/2507","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041313483","display_name":"Benjamin George Cleland","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Benjamin George Cleland","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5041313483"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8450000286102295},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.6019999980926514},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.6909999847412109},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.7250000238418579},{"id":"https://openalex.org/keywords/eligibility-traces","display_name":"eligibility traces","score":0.8999999761581421},{"id":"https://openalex.org/keywords/discounting","display_name":"discounting","score":0.8080000281333923},{"id":"https://openalex.org/keywords/tabular-representation","display_name":"tabular representation","score":0.8330000042915344},{"id":"https://openalex.org/keywords/hashing","display_name":"hashing","score":0.7559999823570251},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.8320000171661377},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.8199999928474426},{"id":"https://openalex.org/keywords/driving-simulation","display_name":"driving simulation","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6644297242164612},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5990179181098938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3617643415927887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3450106680393219},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3206775188446045},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07873380184173584}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/2507","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10289/2507","pdf_url":"https://hdl.handle.net/10289/2507","source":{"id":"https://openalex.org/S4306400944","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I52179390","host_organization_name":"University of Waikato","host_organization_lineage":["https://openalex.org/I52179390"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.125.7697","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.125.7697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://adt.waikato.ac.nz/uploads/approved/adt-uow20060517.135213/public/02whole.pdf","raw_type":"text"},{"id":"mag:1562264016","doi":null,"is_oa":false,"landing_page_url":"https://researchcommons.waikato.ac.nz/handle/10289/2507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/2507","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10289/2507","pdf_url":"https://hdl.handle.net/10289/2507","source":{"id":"https://openalex.org/S4306400944","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I52179390","host_organization_name":"University of Waikato","host_organization_lineage":["https://openalex.org/I52179390"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1562264016.pdf","grobid_xml":"https://content.openalex.org/works/W1562264016.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W36347840","https://openalex.org/W51508254","https://openalex.org/W69985676","https://openalex.org/W70929694","https://openalex.org/W131709709","https://openalex.org/W139877375","https://openalex.org/W1028811162","https://openalex.org/W1491843047","https://openalex.org/W1492518272","https://openalex.org/W1539216098","https://openalex.org/W1547105496","https://openalex.org/W1555801537","https://openalex.org/W1583380718","https://openalex.org/W1592847719","https://openalex.org/W1608650045","https://openalex.org/W1640646391","https://openalex.org/W1657674574","https://openalex.org/W1730118753","https://openalex.org/W1783866091","https://openalex.org/W1820996291","https://openalex.org/W1966195676","https://openalex.org/W1980035368","https://openalex.org/W2009384474","https://openalex.org/W2033976720","https://openalex.org/W2062431974","https://openalex.org/W2064675550","https://openalex.org/W2105336508","https://openalex.org/W2107977784","https://openalex.org/W2109910161","https://openalex.org/W2114451917","https://openalex.org/W2121517924","https://openalex.org/W2122410182","https://openalex.org/W2126598894","https://openalex.org/W2131600418","https://openalex.org/W2137466452","https://openalex.org/W2141559645","https://openalex.org/W2145739724","https://openalex.org/W2158282517","https://openalex.org/W2158548602","https://openalex.org/W2169300227","https://openalex.org/W2198041288","https://openalex.org/W2914656440"],"related_works":["https://openalex.org/W7043276904","https://openalex.org/W7097611718","https://openalex.org/W3114462285","https://openalex.org/W3139014398","https://openalex.org/W2981194798","https://openalex.org/W3110592977","https://openalex.org/W2186183687","https://openalex.org/W4414638646","https://openalex.org/W3135068795","https://openalex.org/W4404306497"],"abstract_inverted_index":{"This":[0,63,122,268],"thesis":[1],"investigates":[2],"the":[3,15,19,61,78,87,91,94,119,136,159,164,182,187,209,221,234,237,248,270,286,289,306,313],"use":[4,38],"of":[5,18,41,48,51,57,93,105,166,176,186,219,236,283,288],"reinforcement":[6,301],"learning":[7,129,138,210,249,271,302],"to":[8,10,29,80,84,102,117,161,180,213,224,232,246],"learn":[9],"drive":[11],"a":[12,45,66,103,113,174,280,293,317],"racecar":[13],"in":[14,86],"simulated":[16],"environment":[17],"Robot":[20,307],"Automobile":[21,308],"Racing":[22,309],"Simulator.":[23],"Real-life":[24],"race":[25],"driving":[26,65],"is":[27,123,130,139,146,190,195,201,203,255,296],"known":[28],"be":[30,81,100,214,225],"difficult":[31],"for":[32,69,315],"humans,":[33],"and":[34,55,71,132,135,149,157,173,217,261,311,320],"expert":[35],"human":[36],"drivers":[37],"complex":[39,155],"sequences":[40],"actions.":[42],"There":[43],"are":[44,171,178,242],"large":[46],"number":[47],"variables,":[49],"some":[50],"which":[52,58],"change":[53],"stochastically":[54],"all":[56],"may":[59,99],"affect":[60],"outcome.":[62],"makes":[64],"promising":[67],"domain":[68],"testing":[70],"developing":[72],"Machine":[73],"Learning":[74],"techniques":[75],"that":[76],"have":[77],"potential":[79],"robust":[82],"enough":[83],"work":[85,98,304],"real":[88],"world.":[89],"Therefore":[90],"principles":[92],"algorithms":[95],"from":[96],"this":[97,150,220],"applicable":[101],"range":[104],"problems.":[106],"\\n":[107],"\\nThe":[108],"investigation":[109,160],"starts":[110],"by":[111,229,259,264,279,292],"finding":[112],"suitable":[114],"data":[115],"structure":[116],"represent":[118],"information":[120],"learnt.":[121],"tested":[124,172],"using":[125,230,265],"supervised":[126,137],"learning.":[127,167],"Reinforcement":[128],"added":[131],"roughly":[133],"tuned,":[134],"then":[140],"removed.":[141],"A":[142],"simple":[143],"tabular":[144,253,290],"representation":[145,254],"found":[147,179],"satisfactory,":[148],"avoids":[151],"difficulties":[152],"with":[153,244],"more":[154,250,257,262,318],"methods":[156],"allows":[158],"concentrate":[162],"on":[163],"essentials":[165],"Various":[168],"reward":[169],"sources":[170],"combination":[175],"three":[177],"produce":[181],"best":[183],"performance.":[184],"Exploration":[185],"problem":[188],"space":[189],"investigated.":[191],"Results":[192],"show":[193,300],"exploration":[194],"essential":[196],"but":[197,272],"controlling":[198],"how":[199],"much":[200],"done":[202],"also":[204],"important.":[205],"It":[206],"turns":[207],"out":[208],"episodes":[211],"need":[212],"very":[215],"long":[216],"because":[218],"task":[222],"needs":[223],"treated":[226],"as":[227],"continuous":[228],"discounting":[231],"limit":[233],"size":[235],"variables":[238],"stored.":[239],"Eligibility":[240],"traces":[241],"used":[243],"success":[245],"make":[247],"efficient.":[251],"The":[252,276],"made":[256],"compact":[258],"hashing":[260],"accurate":[263],"smaller":[266],"buckets.":[267],"slows":[269],"produces":[273],"better":[274],"driving.":[275],"improvement":[277],"given":[278],"rough":[281],"form":[282],"generalisation":[284],"indicates":[285],"replacement":[287],"method":[291],"function":[294],"approximator":[295],"warranted.":[297],"These":[298],"results":[299],"can":[303],"within":[305],"Simulator,":[310],"lay":[312],"foundations":[314],"building":[316],"efficient":[319],"competitive":[321],"agent.":[322]},"counts_by_year":[],"updated_date":"2026-08-31T07:19:18.363097","created_date":"2016-06-24T00:00:00"}