{"id":"https://openalex.org/W4307490062","doi":"https://doi.org/10.1613/jair.1.13854","title":"Low-Rank Representation of Reinforcement Learning Policies","display_name":"Low-Rank Representation of Reinforcement Learning Policies","publication_year":2022,"publication_date":"2022-10-27","ids":{"openalex":"https://openalex.org/W4307490062","doi":"https://doi.org/10.1613/jair.1.13854"},"language":"en","primary_location":{"id":"doi:10.1613/jair.1.13854","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.13854","pdf_url":"https://jair.org/index.php/jair/article/download/13854/26856","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jair.org/index.php/jair/article/download/13854/26856","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114106696","display_name":"Bogdan Mazoure","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Bogdan Mazoure","raw_affiliation_strings":["a:1:{s:5:\"en_US\";s:17:\"McGill University\";}","s:17:\"McGill University\"","a:1:{s:5:\"en_US\""],"affiliations":[{"raw_affiliation_string":"a:1:{s:5:\"en_US\";s:17:\"McGill University\";}","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"s:17:\"McGill University\"","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"a:1:{s:5:\"en_US\"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080464225","display_name":"Thang Doan","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Thang Doan","raw_affiliation_strings":["McGill University"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379455","display_name":"Tianyu Li","orcid":"https://orcid.org/0000-0003-1206-1022"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tianyu Li","raw_affiliation_strings":["McGill University"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004592090","display_name":"Vladimir Makarenkov","orcid":"https://orcid.org/0000-0003-3753-5925"},"institutions":[{"id":"https://openalex.org/I4210108269","display_name":"Salam University","ror":"https://ror.org/01g0sat63","country_code":"AF","type":"education","lineage":["https://openalex.org/I4210108269"]}],"countries":["AF"],"is_corresponding":false,"raw_author_name":"Vladimir Makarenkov","raw_affiliation_strings":["UQ\u00c0M University"],"affiliations":[{"raw_affiliation_string":"UQ\u00c0M University","institution_ids":["https://openalex.org/I4210108269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA","IL"],"is_corresponding":false,"raw_author_name":"Joelle Pineau","raw_affiliation_strings":["McGill University; Facebook AI Research; CIFAR AI Chair","CIFAR AI Chair","Facebook AI Research","McGill University"],"affiliations":[{"raw_affiliation_string":"McGill University; Facebook AI Research; CIFAR AI Chair","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"CIFAR AI Chair","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["McGill University; DeepMind; CIFAR AI Chair","CIFAR AI Chair","McGill University","DeepMind"],"affiliations":[{"raw_affiliation_string":"McGill University; DeepMind; CIFAR AI Chair","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"CIFAR AI Chair","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023766963","display_name":"Guillaume Rabusseau","orcid":"https://orcid.org/0000-0001-8090-2810"},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Guillaume Rabusseau","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al; CIFAR AI Chair","CIFAR AI Chair","Universit\u00e9 de Montr\u00e9al"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al; CIFAR AI Chair","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"CIFAR AI Chair","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5114106696"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10978431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"75","issue":null,"first_page":"597","last_page":"636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9190999865531921,"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/reproducing-kernel-hilbert-space","display_name":"Reproducing kernel Hilbert space","score":0.8715937733650208},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.841230034828186},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6670258641242981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.664857029914856},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6600215435028076},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.593201756477356},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5641017556190491},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5264473557472229},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5097357630729675},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4978909492492676},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.45921561121940613},{"id":"https://openalex.org/keywords/hilbert-curve","display_name":"Hilbert curve","score":0.4136904180049896},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38517385721206665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3433045446872711},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.322543740272522},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30682697892189026},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.297641396522522},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1783982813358307},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.10580301284790039},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07161712646484375},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.06555411219596863}],"concepts":[{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.8715937733650208},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.841230034828186},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6670258641242981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.664857029914856},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6600215435028076},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.593201756477356},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5641017556190491},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5264473557472229},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5097357630729675},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4978909492492676},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.45921561121940613},{"id":"https://openalex.org/C2781142347","wikidata":"https://www.wikidata.org/wiki/Q1366592","display_name":"Hilbert curve","level":2,"score":0.4136904180049896},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38517385721206665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3433045446872711},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.322543740272522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30682697892189026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.297641396522522},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1783982813358307},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.10580301284790039},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07161712646484375},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.06555411219596863},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1613/jair.1.13854","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.13854","pdf_url":"https://jair.org/index.php/jair/article/download/13854/26856","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1613/jair.1.13854","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.13854","pdf_url":"https://jair.org/index.php/jair/article/download/13854/26856","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307490062.pdf","grobid_xml":"https://content.openalex.org/works/W4307490062.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W15601695","https://openalex.org/W35556542","https://openalex.org/W41554520","https://openalex.org/W1538912020","https://openalex.org/W1543510660","https://openalex.org/W1575592356","https://openalex.org/W1771410628","https://openalex.org/W1827128995","https://openalex.org/W1845972764","https://openalex.org/W1924935520","https://openalex.org/W1981490327","https://openalex.org/W1983161979","https://openalex.org/W1986078872","https://openalex.org/W1986830331","https://openalex.org/W2006859604","https://openalex.org/W2014729048","https://openalex.org/W2025533349","https://openalex.org/W2029763864","https://openalex.org/W2033972076","https://openalex.org/W2046513829","https://openalex.org/W2053572490","https://openalex.org/W2058631965","https://openalex.org/W2098914003","https://openalex.org/W2104128541","https://openalex.org/W2112177269","https://openalex.org/W2118980425","https://openalex.org/W2119717200","https://openalex.org/W2131904374","https://openalex.org/W2155027007","https://openalex.org/W2156168464","https://openalex.org/W2158733996","https://openalex.org/W2162798864","https://openalex.org/W2167176849","https://openalex.org/W2254249950","https://openalex.org/W2356031020","https://openalex.org/W2549401308","https://openalex.org/W2561828331","https://openalex.org/W2565370028","https://openalex.org/W2590359093","https://openalex.org/W2594877703","https://openalex.org/W2602963933","https://openalex.org/W2618318883","https://openalex.org/W2781726626","https://openalex.org/W2788089389","https://openalex.org/W2803974723","https://openalex.org/W2898827265","https://openalex.org/W2949361666","https://openalex.org/W2952902960","https://openalex.org/W2962821147","https://openalex.org/W2963864421","https://openalex.org/W2964278893","https://openalex.org/W2970161765","https://openalex.org/W2972435663","https://openalex.org/W2986329025","https://openalex.org/W3037134744","https://openalex.org/W4205621617","https://openalex.org/W4229782167","https://openalex.org/W4238969030","https://openalex.org/W4247305511","https://openalex.org/W4251085907","https://openalex.org/W4254013129","https://openalex.org/W4292683553","https://openalex.org/W4294555834","https://openalex.org/W4297779625","https://openalex.org/W4298023569","https://openalex.org/W4298876402"],"related_works":["https://openalex.org/W2374023116","https://openalex.org/W4299118182","https://openalex.org/W4285290579","https://openalex.org/W1986863144","https://openalex.org/W3134083315","https://openalex.org/W4319083788","https://openalex.org/W2948180181","https://openalex.org/W2964184113","https://openalex.org/W4298112926","https://openalex.org/W2018264451"],"abstract_inverted_index":{"We":[0,69],"propose":[1],"a":[2,16,23,88],"general":[3],"framework":[4,13],"for":[5,8],"policy":[6,21,94],"representation":[7],"reinforcement":[9],"learning":[10],"tasks.":[11],"This":[12],"involves":[14],"finding":[15],"low-dimensional":[17,89],"embedding":[18],"of":[19,31,46],"the":[20,43,47,81,92],"on":[22,42,73],"reproducing":[24],"kernel":[25],"Hilbert":[26],"space":[27,90],"(RKHS).":[28],"The":[29,77],"usage":[30],"RKHS":[32],"based":[33],"methods":[34],"allows":[35],"us":[36],"to":[37],"derive":[38],"strong":[39],"theoretical":[40],"guarantees":[41,51],"expected":[44],"return":[45],"reconstructed":[48],"policy.":[49],"Such":[50],"are":[52,59],"typically":[53],"lacking":[54],"in":[55,62,87,99],"black-box":[56],"models,":[57],"but":[58],"very":[60],"desirable":[61],"tasks":[63],"requiring":[64],"stability":[65],"and":[66],"convergence":[67],"guarantees.":[68],"conduct":[70],"several":[71],"experiments":[72],"classic":[74],"RL":[75],"domains.":[76],"results":[78],"confirm":[79],"that":[80],"policies":[82],"can":[83],"be":[84],"robustly":[85],"represented":[86],"while":[91],"embedded":[93],"incurs":[95],"almost":[96],"no":[97],"decrease":[98],"returns.":[100]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}