{"id":"https://openalex.org/W2014081627","doi":"https://doi.org/10.1109/adprl.2014.7010640","title":"Using supervised training signals of observable state dynamics to speed-up and improve reinforcement learning","display_name":"Using supervised training signals of observable state dynamics to speed-up and improve reinforcement learning","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2014081627","doi":"https://doi.org/10.1109/adprl.2014.7010640","mag":"2014081627"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5086517426","display_name":"Daniel L. Elliott","orcid":"https://orcid.org/0000-0001-9125-592X"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel L Elliott","raw_affiliation_strings":["Dept of Computer Science, Colorado State University","[Department of Computer Science, Colorado State University]"],"affiliations":[{"raw_affiliation_string":"Dept of Computer Science, Colorado State University","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"[Department of Computer Science, Colorado State University]","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036335957","display_name":"Charles W. Anderson","orcid":"https://orcid.org/0000-0001-7392-3840"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Anderson","raw_affiliation_strings":["Dept of Computer Science, Colorado State University","[Department of Computer Science, Colorado State University]"],"affiliations":[{"raw_affiliation_string":"Dept of Computer Science, Colorado State University","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"[Department of Computer Science, Colorado State University]","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086517426"],"corresponding_institution_ids":["https://openalex.org/I92446798"],"apc_list":null,"apc_paid":null,"fwci":0.818,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80169811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"24","issue":null,"first_page":"1","last_page":"8"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9900000095367432,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9898999929428101,"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":0.9019171595573425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7406100630760193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6167735457420349},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5934003591537476},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5663855671882629},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49393683671951294},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48245006799697876},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4696822762489319},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4572129249572754},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4407746195793152},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.43984532356262207},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12495541572570801},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10246053338050842},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.06875148415565491},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06704097986221313}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9019171595573425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7406100630760193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6167735457420349},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5934003591537476},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5663855671882629},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49393683671951294},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48245006799697876},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4696822762489319},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4572129249572754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4407746195793152},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.43984532356262207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12495541572570801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10246053338050842},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.06875148415565491},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06704097986221313},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2014.7010640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1480877541","https://openalex.org/W1686514609","https://openalex.org/W1988688219","https://openalex.org/W2087347031","https://openalex.org/W2121863487","https://openalex.org/W2144416853","https://openalex.org/W2168342951","https://openalex.org/W2283489016","https://openalex.org/W2477884503","https://openalex.org/W4214717370","https://openalex.org/W6628628909","https://openalex.org/W6637317880","https://openalex.org/W6681194083","https://openalex.org/W6695255930"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W2742483371","https://openalex.org/W3038962357","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3099153698","https://openalex.org/W3087814763","https://openalex.org/W2025663273"],"abstract_inverted_index":{"A":[0],"common":[1],"complaint":[2],"about":[3],"reinforcement":[4],"learning":[5],"(RL)":[6],"is":[7,10,24,58,72,107],"that":[8,101],"it":[9],"too":[11],"slow":[12],"to":[13,36,52,60,84],"learn":[14],"a":[15,33,48,65,85],"value":[16],"function":[17],"which":[18],"gives":[19],"good":[20],"performance.":[21,114],"This":[22,30],"issue":[23],"exacerbated":[25],"in":[26],"continuous":[27],"state":[28,62],"spaces.":[29],"paper":[31],"presents":[32],"straight-forward":[34],"approach":[35,78],"speeding-up":[37],"and":[38],"even":[39],"improving":[40],"RL":[41,88,113],"solutions":[42],"by":[43],"reusing":[44],"features":[45,103],"learned":[46,104],"during":[47,105],"pre-training":[49,71,106],"phase":[50],"prior":[51],"Q-learning.":[53],"During":[54],"pre-training,":[55],"the":[56,75,96,102,108,111],"agent":[57],"taught":[59],"predict":[61],"change":[63],"given":[64],"state/action":[66],"pair.":[67],"The":[68,93],"effect":[69],"of":[70,87,95],"examined":[73],"using":[74],"model-free":[76],"Q-learning":[77],"but":[79],"could":[80],"readily":[81],"be":[82],"applied":[83],"number":[86],"approaches":[89],"including":[90],"model-based":[91],"RL.":[92],"analysis":[94],"results":[97],"provides":[98],"ample":[99],"evidence":[100],"reason":[109],"behind":[110],"improved":[112]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}