{"id":"https://openalex.org/W2552352987","doi":"https://doi.org/10.1109/ijcnn.2016.7727678","title":"Manifold regularization based approximate value iteration for learning control","display_name":"Manifold regularization based approximate value iteration for learning control","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2552352987","doi":"https://doi.org/10.1109/ijcnn.2016.7727678","mag":"2552352987"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2016.7727678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","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/A5100442403","display_name":"Hongliang Li","orcid":"https://orcid.org/0000-0001-5387-0825"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongliang Li","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100811145","display_name":"Miao He","orcid":"https://orcid.org/0009-0003-3400-8123"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao He","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031511996","display_name":"Xunan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunan Zhang","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113672506","display_name":"Changrui Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changrui Ren","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100442403"],"corresponding_institution_ids":["https://openalex.org/I4210126794"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13455497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"3717","last_page":"3722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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/T12676","display_name":"Machine Learning and ELM","score":0.9767000079154968,"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":0.7673021554946899},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7381770610809326},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6227961182594299},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5885637998580933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5794780254364014},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5471639633178711},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5157304406166077},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46032917499542236},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.45847633481025696},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.433262437582016},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4096289575099945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3760758638381958},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35798364877700806},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35300207138061523}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7673021554946899},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7381770610809326},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6227961182594299},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5885637998580933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5794780254364014},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5471639633178711},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5157304406166077},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46032917499542236},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.45847633481025696},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.433262437582016},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4096289575099945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3760758638381958},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35798364877700806},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35300207138061523},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2016.7727678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W192920577","https://openalex.org/W560518094","https://openalex.org/W1506832649","https://openalex.org/W1617381654","https://openalex.org/W1626155273","https://openalex.org/W1988523476","https://openalex.org/W1989855774","https://openalex.org/W1997112725","https://openalex.org/W1999678919","https://openalex.org/W1999912147","https://openalex.org/W2030038728","https://openalex.org/W2042184006","https://openalex.org/W2050838777","https://openalex.org/W2052399669","https://openalex.org/W2054083798","https://openalex.org/W2068949505","https://openalex.org/W2072054128","https://openalex.org/W2104290444","https://openalex.org/W2117355432","https://openalex.org/W2120346334","https://openalex.org/W2128812357","https://openalex.org/W2134284153","https://openalex.org/W2135574445","https://openalex.org/W2151416233","https://openalex.org/W2160284799","https://openalex.org/W2161795906","https://openalex.org/W2487144912","https://openalex.org/W2586680856","https://openalex.org/W2997701990","https://openalex.org/W3027095131","https://openalex.org/W4214717370","https://openalex.org/W4245296547","https://openalex.org/W4285719527","https://openalex.org/W4307347247","https://openalex.org/W6675747103","https://openalex.org/W6677549092","https://openalex.org/W6677737365","https://openalex.org/W6679100793","https://openalex.org/W6680088802","https://openalex.org/W6682074005","https://openalex.org/W6683607656","https://openalex.org/W6683841269"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2156021013","https://openalex.org/W2016648086","https://openalex.org/W4399157305","https://openalex.org/W3105579180","https://openalex.org/W1574958246"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"develop":[4],"a":[5,90],"model-free":[6],"and":[7,20,63,75,81],"data":[8],"efficient":[9],"batch":[10],"reinforcement":[11],"learning":[12,15,59],"algorithm":[13,26],"for":[14,42],"control":[16,92],"of":[17,54,69,83],"continuous":[18],"state-space":[19],"discounted-reward":[21],"Markov":[22],"decision":[23],"processes.":[24],"This":[25],"is":[27,87],"an":[28],"approximate":[29],"value":[30,72],"iteration":[31],"which":[32],"uses":[33],"the":[34,51,55,67,70,76,84,95],"manifold":[35],"regularization":[36],"method":[37],"to":[38],"learn":[39],"feature":[40],"representations":[41],"Q-value":[43],"function":[44,73],"approximation.":[45],"The":[46,79],"learned":[47,77],"features":[48],"can":[49,65],"preserve":[50],"intrinsic":[52],"geometry":[53],"state":[56],"space":[57],"by":[58],"on":[60,89],"collected":[61],"samples,":[62],"thus":[64],"improve":[66],"quality":[68],"final":[71],"estimate":[74],"policy.":[78],"effectiveness":[80],"efficiency":[82],"proposed":[85],"scheme":[86],"evaluated":[88],"benchmark":[91],"task,":[93],"i.e.,":[94],"inverted":[96],"pendulum":[97],"balancing":[98],"problem.":[99]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}