{"id":"https://openalex.org/W3199004685","doi":"https://doi.org/10.1109/access.2021.3112498","title":"Effects of Sampling and Prediction Horizon in Reinforcement Learning","display_name":"Effects of Sampling and Prediction Horizon in Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3199004685","doi":"https://doi.org/10.1109/access.2021.3112498","mag":"3199004685"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3112498","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3112498","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09536718.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09536718.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065280230","display_name":"Pavel Osinenko","orcid":"https://orcid.org/0000-0002-6184-3293"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Pavel Osinenko","raw_affiliation_strings":["Computational and Data Science and Engineering, Skolkovo Institute of Science and Technology, Russia. (e-mail: p.osinenko@gmail.com)","Computational and Data Science and Engineering, Skolkovo Institute of Science and Technology, Russia"],"raw_orcid":"https://orcid.org/0000-0002-6184-3293","affiliations":[{"raw_affiliation_string":"Computational and Data Science and Engineering, Skolkovo Institute of Science and Technology, Russia. (e-mail: p.osinenko@gmail.com)","institution_ids":["https://openalex.org/I125989756"]},{"raw_affiliation_string":"Computational and Data Science and Engineering, Skolkovo Institute of Science and Technology, Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051035411","display_name":"Dmitrii Dobriborsci","orcid":"https://orcid.org/0000-0002-1091-7459"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitrii Dobriborsci","raw_affiliation_strings":["Computational and Data Science and Engineering, Skolkovo Institute of Science and Technology, Russia"],"raw_orcid":"https://orcid.org/0000-0002-1091-7459","affiliations":[{"raw_affiliation_string":"Computational and Data Science and Engineering, Skolkovo Institute of Science and Technology, Russia","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065280230"],"corresponding_institution_ids":["https://openalex.org/I125989756"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.8189,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78101212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"127611","last_page":"127618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9973999857902527,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7277166843414307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6379290819168091},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.5043903589248657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5023629665374756},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4841097593307495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4789055585861206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16658943891525269},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09343293309211731}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7277166843414307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6379290819168091},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.5043903589248657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023629665374756},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4841097593307495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4789055585861206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16658943891525269},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09343293309211731},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3112498","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3112498","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09536718.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9d2e21415a7f431781e029be91d5b1a3","is_oa":true,"landing_page_url":"https://doaj.org/article/9d2e21415a7f431781e029be91d5b1a3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 127611-127618 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3112498","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3112498","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09536718.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324442","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3199004685.pdf","grobid_xml":"https://content.openalex.org/works/W3199004685.grobid-xml"},"referenced_works_count":83,"referenced_works":["https://openalex.org/W9639216","https://openalex.org/W178292676","https://openalex.org/W215834334","https://openalex.org/W1484219741","https://openalex.org/W1588741926","https://openalex.org/W1967178780","https://openalex.org/W1977655452","https://openalex.org/W1985178683","https://openalex.org/W1987489142","https://openalex.org/W1988505764","https://openalex.org/W1991929271","https://openalex.org/W2009396486","https://openalex.org/W2019348145","https://openalex.org/W2027968610","https://openalex.org/W2028678875","https://openalex.org/W2031096847","https://openalex.org/W2035589416","https://openalex.org/W2040161377","https://openalex.org/W2040871402","https://openalex.org/W2041109651","https://openalex.org/W2045332133","https://openalex.org/W2049156549","https://openalex.org/W2050204013","https://openalex.org/W2052255798","https://openalex.org/W2102737570","https://openalex.org/W2102879106","https://openalex.org/W2110040537","https://openalex.org/W2130005755","https://openalex.org/W2134673975","https://openalex.org/W2165545652","https://openalex.org/W2182517942","https://openalex.org/W2190343394","https://openalex.org/W2196218134","https://openalex.org/W2257979135","https://openalex.org/W2607292863","https://openalex.org/W2765201826","https://openalex.org/W2767143830","https://openalex.org/W2799225442","https://openalex.org/W2889731659","https://openalex.org/W2902624920","https://openalex.org/W2902907165","https://openalex.org/W2913577890","https://openalex.org/W2947797543","https://openalex.org/W2954409383","https://openalex.org/W2963414638","https://openalex.org/W2970161765","https://openalex.org/W2970351915","https://openalex.org/W2971091362","https://openalex.org/W2980297602","https://openalex.org/W2982316857","https://openalex.org/W2995298643","https://openalex.org/W2998959212","https://openalex.org/W3016548437","https://openalex.org/W3021034371","https://openalex.org/W3030804074","https://openalex.org/W3034859493","https://openalex.org/W3035230405","https://openalex.org/W3035644784","https://openalex.org/W3036251984","https://openalex.org/W3038887435","https://openalex.org/W3041857652","https://openalex.org/W3092793148","https://openalex.org/W3100539220","https://openalex.org/W3150570724","https://openalex.org/W4211081235","https://openalex.org/W4211147054","https://openalex.org/W4240428193","https://openalex.org/W4287743239","https://openalex.org/W4287828546","https://openalex.org/W6754302822","https://openalex.org/W6758907457","https://openalex.org/W6763348168","https://openalex.org/W6764823562","https://openalex.org/W6767019922","https://openalex.org/W6771217966","https://openalex.org/W6771598146","https://openalex.org/W6772082531","https://openalex.org/W6775261052","https://openalex.org/W6776556448","https://openalex.org/W6778083458","https://openalex.org/W6779692524","https://openalex.org/W6780168246","https://openalex.org/W6780349915"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Plain":[0],"reinforcement":[1],"learning":[2,21],"(RL)":[3],"may":[4],"be":[5],"prone":[6],"to":[7,23,31,61],"loss":[8],"of":[9,41,46,77,88,91,120,125,154,161],"convergence,":[10],"constraint":[11],"violation,":[12],"unexpected":[13],"performance,":[14],"etc.":[15],"Commonly,":[16],"RL":[17,47,66,89,168],"agents":[18,149,169],"undergo":[19],"extensive":[20],"stages":[22],"achieve":[24],"acceptable":[25],"functionality.":[26],"This":[27],"is":[28,43,67,101,139],"in":[29,103,129,140],"contrast":[30],"classical":[32],"control":[33,53,144],"algorithms":[34],"which":[35,138],"are":[36,81],"typically":[37],"model-based.":[38],"An":[39],"direction":[40],"research":[42],"the":[44,62,75,78,109,118,148,167],"fusion":[45],"with":[48,70,133,150],"such":[49],"algorithms,":[50],"especially":[51],"model-predictive":[52],"(MPC).":[54],"This,":[55],"however,":[56],"introduces":[57],"new":[58],"hyper-parameters":[59],"related":[60],"prediction":[63,121],"horizon.":[64],"Furthermore,":[65],"usually":[68],"concerned":[69],"Markov":[71],"decision":[72],"processes.":[73],"But":[74],"most":[76],"real":[79],"environments":[80],"not":[82],"time-discrete.":[83],"The":[84,156],"factual":[85],"physical":[86],"setting":[87],"consists":[90],"a":[92,96,130,134,142,151,159,162],"digital":[93],"agent":[94,110],"and":[95,123],"time-continuous":[97],"dynamical":[98],"system.":[99],"There":[100],"thus,":[102],"fact,":[104],"yet":[105],"another":[106],"hyper-parameter":[107],"\u2013":[108],"sampling":[111,124,157],"time.":[112],"In":[113],"this":[114],"paper,":[115],"we":[116],"investigate":[117],"effects":[119],"horizon":[122],"two":[126],"hybrid":[127],"RL-MPC-agents":[128],"case":[131],"study":[132],"mobile":[135],"robot":[136],"parking,":[137],"turn":[141],"canonical":[143],"problem.":[145],"We":[146],"benchmark":[147],"simple":[152],"variant":[153],"MPC.":[155],"showed":[158],"kind":[160],"\u201csweet":[163],"spot\u201d":[164],"behavior,":[165],"whereas":[166],"demonstrated":[170],"merits":[171],"at":[172],"shorter":[173],"horizons.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}