{"id":"https://openalex.org/W1521228173","doi":"https://doi.org/10.1109/icsmc.2005.1571636","title":"Comparing Different Methods to Speed Up Reinforcement Learning in a Complex Domain","display_name":"Comparing Different Methods to Speed Up Reinforcement Learning in a Complex Domain","publication_year":2006,"publication_date":"2006-01-18","ids":{"openalex":"https://openalex.org/W1521228173","doi":"https://doi.org/10.1109/icsmc.2005.1571636","mag":"1521228173"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2005.1571636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2005.1571636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Systems, Man and Cybernetics","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/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690"},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"M. Riedmiller","raw_affiliation_strings":["University of Osnabr\u00fcck, Osnabruck, Germany"],"affiliations":[{"raw_affiliation_string":"University of Osnabr\u00fcck, Osnabruck, Germany","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023055699","display_name":"Daniel Withopf","orcid":null},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Withopf","raw_affiliation_strings":["Robert Bosch Gmbh, Hildesheim, Germany"],"affiliations":[{"raw_affiliation_string":"Robert Bosch Gmbh, Hildesheim, Germany","institution_ids":["https://openalex.org/I889804353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041323275"],"corresponding_institution_ids":["https://openalex.org/I170658231"],"apc_list":null,"apc_paid":null,"fwci":0.4518,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71282854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"3185","last_page":"3190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10603","display_name":"Smart Grid Energy Management","score":0.977400004863739,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12761","display_name":"Data Stream Mining Techniques","score":0.9714000225067139,"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":0.8677823543548584},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8409849405288696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7137841582298279},{"id":"https://openalex.org/keywords/successor-cardinal","display_name":"Successor cardinal","score":0.7006622552871704},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6628371477127075},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6527281999588013},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6255647540092468},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6009705066680908},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5236054062843323},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5043069124221802},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4951399862766266},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.454842209815979},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4334769546985626},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42079460620880127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4203651249408722},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4170992076396942},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40250176191329956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2980131506919861},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2155826985836029}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8677823543548584},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8409849405288696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7137841582298279},{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.7006622552871704},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6628371477127075},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6527281999588013},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6255647540092468},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6009705066680908},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5236054062843323},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5043069124221802},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4951399862766266},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.454842209815979},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4334769546985626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42079460620880127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4203651249408722},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4170992076396942},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40250176191329956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2980131506919861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2155826985836029},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2005.1571636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2005.1571636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W79394677","https://openalex.org/W1488730473","https://openalex.org/W1592847719","https://openalex.org/W1839010533","https://openalex.org/W2109910161","https://openalex.org/W2119567691","https://openalex.org/W2158548602","https://openalex.org/W2334782222","https://openalex.org/W4298023569","https://openalex.org/W6603137543","https://openalex.org/W6629152578","https://openalex.org/W6638609715","https://openalex.org/W6683443546"],"related_works":["https://openalex.org/W4308702637","https://openalex.org/W3105579180","https://openalex.org/W2808418668","https://openalex.org/W2383312578","https://openalex.org/W2145363145","https://openalex.org/W1574958246","https://openalex.org/W61119710","https://openalex.org/W1521228173","https://openalex.org/W3185269925","https://openalex.org/W1556532828"],"abstract_inverted_index":{"We":[0,45],"introduce":[1],"a":[2,19,32,65],"new":[3],"learning":[4,59,83],"algorithm":[5,29,48],"(semi-DP":[6],"algorithm)":[7],"designed":[8],"for":[9],"MDPs":[10],"(Markov":[11],"decision":[12],"process)":[13],"where":[14],"actions":[15],"either":[16],"lead":[17],"to":[18,24,37,40,53,61],"deterministic":[20],"successor":[21],"state":[22],"or":[23,56],"the":[25,41,58,78,82,87],"terminal":[26],"state.":[27],"The":[28],"only":[30],"needs":[31],"finite":[33],"number":[34],"of":[35,81],"loops":[36],"converge":[38],"exactly":[39],"optimal":[42,88],"action-value":[43],"function.":[44],"compare":[46],"this":[47],"and":[49],"three":[50],"other":[51],"methods":[52],"speed":[54],"up":[55],"simplify":[57],"process":[60],"ordinary":[62],"Q-learning":[63],"in":[64],"soccer":[66],"grid-world.":[67],"Furthermore,":[68],"we":[69],"show":[70],"that":[71],"different":[72],"reward":[73],"functions":[74],"can":[75],"considerably":[76],"change":[77],"convergence":[79],"time":[80],"algorithms":[84],"even":[85],"if":[86],"policy":[89],"remains":[90],"unchanged.":[91]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}