{"id":"https://openalex.org/W2774084538","doi":"https://doi.org/10.1109/iros.2017.8205962","title":"Neural networks for incremental dimensionality reduced reinforcement learning","display_name":"Neural networks for incremental dimensionality reduced reinforcement learning","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2774084538","doi":"https://doi.org/10.1109/iros.2017.8205962","mag":"2774084538"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2017.8205962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8205962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5043639979","display_name":"William J. Curran","orcid":"https://orcid.org/0000-0002-8821-8658"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Curran","raw_affiliation_strings":["Oregon State University, Corvallis, United States"],"affiliations":[{"raw_affiliation_string":"Oregon State University, Corvallis, United States","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001340547","display_name":"Rey Pocius","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rey Pocius","raw_affiliation_strings":["Oregon State University, Corvallis, United States"],"affiliations":[{"raw_affiliation_string":"Oregon State University, Corvallis, United States","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026622322","display_name":"William D. Smart","orcid":"https://orcid.org/0000-0001-6867-5125"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William D. Smart","raw_affiliation_strings":["Oregon State University, Corvallis, United States"],"affiliations":[{"raw_affiliation_string":"Oregon State University, Corvallis, United States","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043639979"],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.17356434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"290","issue":null,"first_page":"1559","last_page":"1565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7580634355545044},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.7299575805664062},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6888673305511475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6539010405540466},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6412110924720764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5710271596908569},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.528733491897583},{"id":"https://openalex.org/keywords/degrees-of-freedom","display_name":"Degrees of freedom (physics and chemistry)","score":0.5279870629310608},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4974546730518341},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48260796070098877},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.4823129177093506},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4581450819969177},{"id":"https://openalex.org/keywords/nonlinear-dimensionality-reduction","display_name":"Nonlinear dimensionality reduction","score":0.42734047770500183},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35949042439460754},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2076702117919922},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1498153805732727},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1463298797607422}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7580634355545044},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7299575805664062},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6888673305511475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539010405540466},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6412110924720764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5710271596908569},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.528733491897583},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.5279870629310608},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4974546730518341},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48260796070098877},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.4823129177093506},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4581450819969177},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.42734047770500183},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35949042439460754},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2076702117919922},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1498153805732727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1463298797607422},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2017.8205962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8205962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W80219033","https://openalex.org/W107583932","https://openalex.org/W1485585868","https://openalex.org/W1515851193","https://openalex.org/W1567001657","https://openalex.org/W1585603966","https://openalex.org/W1832110895","https://openalex.org/W1968876723","https://openalex.org/W1986014385","https://openalex.org/W2001141328","https://openalex.org/W2021004298","https://openalex.org/W2031291740","https://openalex.org/W2053186076","https://openalex.org/W2097381042","https://openalex.org/W2098693229","https://openalex.org/W2100495367","https://openalex.org/W2105732805","https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2123447947","https://openalex.org/W2124267516","https://openalex.org/W2124776405","https://openalex.org/W2129442128","https://openalex.org/W2145301390","https://openalex.org/W2154328025","https://openalex.org/W2154722715","https://openalex.org/W2161966552","https://openalex.org/W2181347294","https://openalex.org/W2203551375","https://openalex.org/W2403765497","https://openalex.org/W2610550445","https://openalex.org/W2617585083","https://openalex.org/W2903420114","https://openalex.org/W3099514962","https://openalex.org/W3144155561","https://openalex.org/W4239390603","https://openalex.org/W4247582681","https://openalex.org/W4250857377","https://openalex.org/W4285719527","https://openalex.org/W6633915131","https://openalex.org/W6674600207","https://openalex.org/W6676014314","https://openalex.org/W6678481081","https://openalex.org/W6683603353","https://openalex.org/W6685777803","https://openalex.org/W6688020001","https://openalex.org/W6712898688","https://openalex.org/W6756879699"],"related_works":["https://openalex.org/W2375574759","https://openalex.org/W2383239174","https://openalex.org/W3088634662","https://openalex.org/W117517268","https://openalex.org/W3162910294","https://openalex.org/W2539700568","https://openalex.org/W1995622179","https://openalex.org/W4391160746","https://openalex.org/W2931531042","https://openalex.org/W2166963679"],"abstract_inverted_index":{"State-of-the-art":[0],"personal":[1],"robots":[2,31],"must":[3],"perform":[4],"complex":[5],"manipulation":[6],"tasks":[7],"to":[8,33,41],"be":[9],"viable":[10],"in":[11,114],"assistive":[12],"scenarios.":[13],"However,":[14],"many":[15],"of":[16,29,87,106],"these":[17,30],"robots,":[18],"like":[19],"the":[20,48,53,98,104,115],"PR2,":[21],"use":[22],"manipulators":[23],"with":[24],"high":[25],"degrees-of-freedom.":[26],"The":[27],"complexity":[28],"lead":[32],"large":[34],"dimensional":[35],"state":[36],"spaces,":[37],"which":[38,51],"are":[39],"difficult":[40],"fully":[42],"explore.":[43],"Our":[44],"previous":[45,85,111],"work":[46,71],"introduced":[47],"IDRRL":[49,76,88],"algorithm,":[50],"compresses":[52],"learning":[54,60],"space":[55,61],"by":[56,89],"transforming":[57],"a":[58,63],"high-dimensional":[59],"onto":[62],"lower-dimensional":[64],"manifold":[65],"while":[66],"preserving":[67],"expressivity.":[68],"In":[69],"this":[70,107],"we":[72],"formally":[73],"prove":[74],"that":[75],"maintains":[77],"PAC-MDP":[78],"guarantees.":[79],"We":[80,102],"then":[81],"improve":[82],"upon":[83],"our":[84,110],"formulation":[86],"introducing":[90],"cascading":[91],"autoencoders":[92],"(CAE)":[93],"for":[94],"dimensionality":[95],"reduction,":[96],"producing":[97],"new":[99],"algorithm":[100],"IDRRL-CAE.":[101],"demonstrate":[103],"improvement":[105],"extension":[108],"over":[109],"formulation,":[112],"IDRRL-PCA,":[113],"Mountain":[116],"Car":[117],"and":[118],"Swimmers":[119],"domains.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}