{"id":"https://openalex.org/W2585033975","doi":"https://doi.org/10.1109/icarcv.2016.7838691","title":"Integrating symmetry of environment by designing special basis functions for value function approximation in reinforcement learning","display_name":"Integrating symmetry of environment by designing special basis functions for value function approximation in reinforcement learning","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2585033975","doi":"https://doi.org/10.1109/icarcv.2016.7838691","mag":"2585033975"},"language":"en","primary_location":{"id":"doi:10.1109/icarcv.2016.7838691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2016.7838691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV)","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/A5054085447","display_name":"Guofang Wang","orcid":"https://orcid.org/0000-0003-2727-2607"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guo-fang Wang","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, ZJU, China"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, ZJU, China","institution_ids":["https://openalex.org/I9842412","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048127669","display_name":"Zhou Fang","orcid":"https://orcid.org/0000-0002-5389-6694"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Fang","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, ZJU, China"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, ZJU, China","institution_ids":["https://openalex.org/I9842412","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100772208","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-7095-4841"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, ZJU, China"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, ZJU, China","institution_ids":["https://openalex.org/I9842412","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741315","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-8515-7773"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["Department of Control Science and Engineering, Zhejiang University, Hangzhou, ZJU, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Zhejiang University, Hangzhou, ZJU, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054085447"],"corresponding_institution_ids":["https://openalex.org/I76130692","https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.4285,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80704101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"20","issue":null,"first_page":"1","last_page":"6"},"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/T10524","display_name":"Traffic control and management","score":0.9728999733924866,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9442999958992004,"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":0.7775127291679382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354507446289062},{"id":"https://openalex.org/keywords/symmetry","display_name":"Symmetry (geometry)","score":0.5073034167289734},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.490002304315567},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4857342839241028},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4502026438713074},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.44967395067214966},{"id":"https://openalex.org/keywords/basis-function","display_name":"Basis function","score":0.43896088004112244},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42877382040023804},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41751474142074585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3708030581474304},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27230530977249146}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7775127291679382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354507446289062},{"id":"https://openalex.org/C2779886137","wikidata":"https://www.wikidata.org/wiki/Q21030012","display_name":"Symmetry (geometry)","level":2,"score":0.5073034167289734},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.490002304315567},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4857342839241028},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4502026438713074},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.44967395067214966},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.43896088004112244},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42877382040023804},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41751474142074585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3708030581474304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27230530977249146},{"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},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarcv.2016.7838691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2016.7838691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1130790960","https://openalex.org/W1604363237","https://openalex.org/W1949804828","https://openalex.org/W1977655452","https://openalex.org/W1997112725","https://openalex.org/W2012069857","https://openalex.org/W2046376809","https://openalex.org/W2068932794","https://openalex.org/W2069300867","https://openalex.org/W2079247031","https://openalex.org/W2084202551","https://openalex.org/W2097498341","https://openalex.org/W2109102709","https://openalex.org/W2113921460","https://openalex.org/W2118556122","https://openalex.org/W2129427976","https://openalex.org/W2134882417","https://openalex.org/W2137375617","https://openalex.org/W2150663697","https://openalex.org/W2162768030","https://openalex.org/W2169209873","https://openalex.org/W2172968643","https://openalex.org/W2175306743","https://openalex.org/W2586680856","https://openalex.org/W4285719527","https://openalex.org/W4300513819","https://openalex.org/W6636142636","https://openalex.org/W6674664616","https://openalex.org/W6680322746","https://openalex.org/W6685247492","https://openalex.org/W6685331716","https://openalex.org/W7034091645"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W3099153698","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,37],"(RL)":[2],"is":[3,100,122],"usually":[4],"regarded":[5],"as":[6,93,173],"tabula":[7],"rasa":[8],"learning,":[9],"and":[10,23,39,59,118,129,148,172],"the":[11,17,20,30,48,76,82,103,119,141,149,158,166,179],"agent":[12],"needs":[13],"to":[14,35,55,74,164,181],"randomly":[15],"explore":[16],"environment,":[18],"so":[19],"time":[21],"consuming":[22],"data":[24,41],"inefficiency":[25],"will":[26],"hinder":[27],"RL":[28,187],"from":[29,51],"real":[31],"application.":[32],"In":[33],"order":[34],"accelerate":[36],"speed":[38,143],"improve":[40],"efficiency,":[42],"in":[43,135],"this":[44,96],"paper":[45],"we":[46,113],"expand":[47],"symmetry":[49,80,169,183],"definition":[50],"finite":[52],"state":[53,57,89],"space":[54,58],"infinite":[56,88],"then":[60],"propose":[61],"designing":[62],"a":[63,174],"special":[64],"type":[65],"of":[66,79,107,126,144,160,168,184],"symmetric":[67,115,161],"basis":[68,162],"functions":[69,163],"for":[70,84],"value":[71],"function":[72],"approximation":[73],"integrate":[75,182],"prior":[77],"knowledge":[78],"about":[81],"environment":[83,185],"large":[85],"or":[86],"even":[87],"space.":[90],"After":[91],"that,":[92],"an":[94],"example,":[95],"particular":[97],"approximate":[98],"structure":[99],"incorporated":[101],"into":[102,186],"policy":[104],"evaluation":[105],"phase":[106],"Least-Square":[108],"Policy":[109],"Iteration":[110],"(LSPI),":[111],"which":[112],"call":[114],"LSPI":[116,139],"(S-LSPI)":[117],"convergence":[120,142],"property":[121,167],"analyzed.":[123],"Simulation":[124],"results":[125],"chain":[127],"walk":[128],"inverted":[130],"pendulum":[131],"balancing":[132],"demonstrate":[133],"that":[134],"contrast":[136],"with":[137],"regular":[138],"(R-LSPI),":[140],"S-LSPI":[145],"increases":[146],"greatly":[147],"computational":[150],"burden":[151],"decreases":[152],"significantly":[153],"simultaneously.":[154],"It":[155],"can":[156],"illustrate":[157],"use":[159],"capture":[165],"very":[170],"well,":[171],"case":[175],"study,":[176],"it":[177],"shows":[178],"promise":[180],"agent.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}