{"id":"https://openalex.org/W2775192669","doi":"https://doi.org/10.1109/iros.2017.8206334","title":"Goal-driven dimensionality reduction for reinforcement learning","display_name":"Goal-driven dimensionality reduction for reinforcement learning","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2775192669","doi":"https://doi.org/10.1109/iros.2017.8206334","mag":"2775192669"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2017.8206334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8206334","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/A5055633714","display_name":"Simone Parisi","orcid":"https://orcid.org/0000-0003-3886-8131"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Simone Parisi","raw_affiliation_strings":["Autonomous Systems Labs, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Labs, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053086200","display_name":"Simon Ramstedt","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Ramstedt","raw_affiliation_strings":["Autonomous Systems Labs, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Labs, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Autonomous Systems Labs, Technical University of Darmstadt, Darmstadt, Germany","Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Labs, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055633714"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":1.1701,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84733307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4634","last_page":"4639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9918000102043152,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8086113929748535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7205276489257812},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6881105899810791},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6304829716682434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6271514296531677},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5311794281005859},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5291669368743896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5007228851318359},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4944584369659424},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4838953912258148},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4828077554702759},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4695993661880493},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4648882746696472},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42918288707733154},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1549316644668579}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8086113929748535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205276489257812},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6881105899810791},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6304829716682434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6271514296531677},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5311794281005859},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5291669368743896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5007228851318359},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4944584369659424},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4838953912258148},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4828077554702759},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4695993661880493},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4648882746696472},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42918288707733154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1549316644668579},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2017.8206334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8206334","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1496685878","https://openalex.org/W1499669280","https://openalex.org/W1771410628","https://openalex.org/W1967066850","https://openalex.org/W1998172110","https://openalex.org/W2011233848","https://openalex.org/W2012587148","https://openalex.org/W2021004298","https://openalex.org/W2027968610","https://openalex.org/W2039134469","https://openalex.org/W2104733512","https://openalex.org/W2106049924","https://openalex.org/W2112264645","https://openalex.org/W2123157758","https://openalex.org/W2123967136","https://openalex.org/W2132301339","https://openalex.org/W2154997814","https://openalex.org/W2157544132","https://openalex.org/W2160284799","https://openalex.org/W2167840144","https://openalex.org/W2187770737","https://openalex.org/W2213381658","https://openalex.org/W2290354866","https://openalex.org/W2473408367","https://openalex.org/W2950471160","https://openalex.org/W2952063594","https://openalex.org/W2963864421","https://openalex.org/W3144155561","https://openalex.org/W4293713648","https://openalex.org/W4297807549","https://openalex.org/W6638018090","https://openalex.org/W6653548176","https://openalex.org/W6675999342","https://openalex.org/W6678157427","https://openalex.org/W6679599164","https://openalex.org/W6683863374","https://openalex.org/W6686922269","https://openalex.org/W6696324988","https://openalex.org/W6720923776"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W1484111231","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W3089231081","https://openalex.org/W2093956241","https://openalex.org/W2354420595"],"abstract_inverted_index":{"Defining":[0],"a":[1,12,74],"state":[2,79,98],"representation":[3],"on":[4,96],"which":[5],"optimal":[6,58],"control":[7],"can":[8,119],"perform":[9],"well":[10],"is":[11],"tedious":[13],"but":[14],"crucial":[15],"process.":[16],"It":[17],"typically":[18],"requires":[19],"expert":[20],"knowledge,":[21],"does":[22,83,91],"not":[23,84,92],"generalize":[24],"straightforwardly":[25],"over":[26],"different":[27],"tasks":[28],"and":[29,100,130,134],"strongly":[30],"influences":[31],"the":[32,35,78,89,97,103,109],"quality":[33,122],"of":[34,52,77,88,105,111],"learned":[36],"controller.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"present":[42],"an":[43,57],"autonomous":[44],"feature":[45],"construction":[46],"method":[47,64,82,118],"for":[48],"learning":[49,106,137],"low-dimensional":[50],"manifolds":[51],"goal-relevant":[53],"features":[54],"jointly":[55],"with":[56,68],"controller":[59,123],"using":[60],"reinforcement":[61],"learning.":[62],"Our":[63],"combines":[65],"information-theoretic":[66],"algorithms":[67],"principal":[69],"component":[70],"analysis":[71],"to":[72],"performs":[73],"return-weighted":[75],"reduction":[76],"representation.":[80],"The":[81],"require":[85],"any":[86],"preprocessing":[87],"data,":[90],"assume":[93],"strong":[94],"restrictions":[95],"representation,":[99],"substantially":[101],"improves":[102],"performance":[104],"by":[107],"reducing":[108],"number":[110],"samples":[112],"required.":[113],"We":[114],"show":[115],"that":[116],"our":[117],"learn":[120],"high":[121],"in":[124],"redundant":[125],"spaces,":[126],"even":[127],"from":[128],"pixels,":[129],"outperforms":[131],"both":[132],"classical":[133],"state-of-the-art":[135],"deep":[136],"approaches.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}