{"id":"https://openalex.org/W4292973684","doi":"https://doi.org/10.1109/tpami.2022.3200726","title":"Information Optimization and Transferable State Abstractions in Deep Reinforcement Learning","display_name":"Information Optimization and Transferable State Abstractions in Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4292973684","doi":"https://doi.org/10.1109/tpami.2022.3200726","pmid":"https://pubmed.ncbi.nlm.nih.gov/35994548"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3200726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3200726","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5032148473","display_name":"Diego Gomez","orcid":"https://orcid.org/0000-0002-4625-233X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Diego Gomez","raw_affiliation_strings":["Departmento de Ingeniería Eléctrica y Electrónica, Colombia","ctrica y Electr&#x00F3","nica, Colombia","a El&#x00E9"],"raw_orcid":"https://orcid.org/0000-0002-4625-233X","affiliations":[{"raw_affiliation_string":"Departmento de Ingeniería Eléctrica y Electrónica, Colombia","institution_ids":[]},{"raw_affiliation_string":"ctrica y Electr&#x00F3","institution_ids":[]},{"raw_affiliation_string":"nica, Colombia","institution_ids":[]},{"raw_affiliation_string":"a El&#x00E9","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010955102","display_name":"Nicanor Quijano","orcid":"https://orcid.org/0000-0002-8688-3195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicanor Quijano","raw_affiliation_strings":["Departmento de Ingeniería Eléctrica y Electrónica, Colombia","a El&#x00E9","ctrica y Electr&#x00F3","nica, Colombia"],"raw_orcid":"https://orcid.org/0000-0002-8688-3195","affiliations":[{"raw_affiliation_string":"Departmento de Ingeniería Eléctrica y Electrónica, Colombia","institution_ids":[]},{"raw_affiliation_string":"a El&#x00E9","institution_ids":[]},{"raw_affiliation_string":"ctrica y Electr&#x00F3","institution_ids":[]},{"raw_affiliation_string":"nica, Colombia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001455035","display_name":"Luis Felipe Giraldo","orcid":"https://orcid.org/0000-0002-2492-4422"},"institutions":[{"id":"https://openalex.org/I162096671","display_name":"Universidad de Los Andes","ror":"https://ror.org/02mhbdp94","country_code":"CO","type":"education","lineage":["https://openalex.org/I162096671"]}],"countries":["CO"],"is_corresponding":false,"raw_author_name":"Luis Felipe Giraldo","raw_affiliation_strings":["Departamento de Ingeniería Biomédica, Universidad de Los Andes, Bogotá, Colombia","a Biom&#x00E9",", Colombia","Departamento de Ingenier&#x00ED"],"raw_orcid":"https://orcid.org/0000-0002-2492-4422","affiliations":[{"raw_affiliation_string":"Departamento de Ingeniería Biomédica, Universidad de Los Andes, Bogotá, Colombia","institution_ids":["https://openalex.org/I162096671"]},{"raw_affiliation_string":"a Biom&#x00E9","institution_ids":[]},{"raw_affiliation_string":", Colombia","institution_ids":[]},{"raw_affiliation_string":"Departamento de Ingenier&#x00ED","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032148473"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4709,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59931775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"45","issue":"4","first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9897000193595886,"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/computer-science","display_name":"Computer science","score":0.8347881436347961},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8294991254806519},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7439936995506287},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7011388540267944},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6921321153640747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6873422861099243},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6280630230903625},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5821331143379211},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5589205026626587},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4819714426994324},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4285967946052551},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4213711619377136},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3753853142261505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8347881436347961},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8294991254806519},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7439936995506287},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7011388540267944},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6921321153640747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6873422861099243},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6280630230903625},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5821331143379211},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5589205026626587},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4819714426994324},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4285967946052551},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4213711619377136},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3753853142261505},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3200726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3200726","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35994548","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35994548","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W48257500","https://openalex.org/W1686946872","https://openalex.org/W1738827650","https://openalex.org/W1994618660","https://openalex.org/W2001685400","https://openalex.org/W2014932765","https://openalex.org/W2061982926","https://openalex.org/W2065279029","https://openalex.org/W2097381042","https://openalex.org/W2105055424","https://openalex.org/W2109910161","https://openalex.org/W2118917307","https://openalex.org/W2119101994","https://openalex.org/W2122925692","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2165545766","https://openalex.org/W2239029832","https://openalex.org/W2273912701","https://openalex.org/W2521862911","https://openalex.org/W2726187156","https://openalex.org/W2738396776","https://openalex.org/W2766447205","https://openalex.org/W2886442201","https://openalex.org/W2891540084","https://openalex.org/W2896084542","https://openalex.org/W2904246096","https://openalex.org/W2904715276","https://openalex.org/W2913403708","https://openalex.org/W2914578055","https://openalex.org/W2916826721","https://openalex.org/W2942538153","https://openalex.org/W2964227312","https://openalex.org/W2971074500","https://openalex.org/W2990747716","https://openalex.org/W3006604032","https://openalex.org/W3016970897","https://openalex.org/W3031644095","https://openalex.org/W3092597801","https://openalex.org/W3103934428","https://openalex.org/W3122690883","https://openalex.org/W3212335243","https://openalex.org/W4214717370","https://openalex.org/W4286910245","https://openalex.org/W4287631403","https://openalex.org/W4287672544","https://openalex.org/W4287996125","https://openalex.org/W4288088514","https://openalex.org/W4294646197","https://openalex.org/W4299879285","https://openalex.org/W4315487473","https://openalex.org/W4383112908","https://openalex.org/W6637108112","https://openalex.org/W6638018090","https://openalex.org/W6640963894","https://openalex.org/W6674600207","https://openalex.org/W6678900246","https://openalex.org/W6685444567","https://openalex.org/W6704571135","https://openalex.org/W6712173889","https://openalex.org/W6719911377","https://openalex.org/W6729906282","https://openalex.org/W6736057607","https://openalex.org/W6740092555","https://openalex.org/W6740222838","https://openalex.org/W6741832103","https://openalex.org/W6744935223","https://openalex.org/W6746569983","https://openalex.org/W6748603076","https://openalex.org/W6750254146","https://openalex.org/W6753190865","https://openalex.org/W6755176883","https://openalex.org/W6756303580","https://openalex.org/W6756840741","https://openalex.org/W6757592117","https://openalex.org/W6758714319","https://openalex.org/W6759008790","https://openalex.org/W6759370769","https://openalex.org/W6762931180","https://openalex.org/W6765044274","https://openalex.org/W6765456200","https://openalex.org/W6767141496","https://openalex.org/W6769570503","https://openalex.org/W6771249860","https://openalex.org/W6771876938","https://openalex.org/W6773516363","https://openalex.org/W6773593885","https://openalex.org/W6779827379","https://openalex.org/W6780559895","https://openalex.org/W6782448357","https://openalex.org/W6783988234","https://openalex.org/W6785193213","https://openalex.org/W6802559433"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W171213352","https://openalex.org/W4310614650"],"abstract_inverted_index":{"While":[0],"humans":[1],"and":[2,9,115,127],"animals":[3],"learn":[4,96,111],"incrementally":[5],"during":[6],"their":[7,11],"lifetimes":[8],"exploit":[10],"experience":[12],"to":[13,23,57,95,110,134],"solve":[14,24,58],"new":[15,42,48,132],"tasks,":[16,80,129],"standard":[17],"deep":[18],"reinforcement":[19],"learning":[20,64],"methods":[21],"specialize":[22],"only":[25],"one":[26],"task":[27],"at":[28],"a":[29,32,47,72,131],"time.":[30],"As":[31],"result,":[33],"the":[34,51,83,121],"information":[35,103],"they":[36],"acquire":[37],"is":[38,76,93,108],"hardly":[39],"reusable":[40],"in":[41,113,124],"situations.":[43],"Here,":[44],"we":[45,89],"introduce":[46],"perspective":[49],"on":[50],"problem":[52],"of":[53,67,85],"leveraging":[54],"prior":[55],"knowledge":[56],"future":[59],"tasks.":[60],"We":[61],"show":[62,90],"that":[63,75,91,119],"discrete":[65],"representations":[66,98],"sensory":[68],"inputs":[69],"can":[70],"provide":[71],"high-level":[73],"abstraction":[74],"common":[77],"across":[78],"multiple":[79],"thus":[81],"facilitating":[82],"transference":[84],"information.":[86],"In":[87],"particular,":[88],"it":[92],"possible":[94],"such":[97],"by":[99],"self-supervision,":[100],"following":[101],"an":[102],"theoretic":[104],"approach.":[105],"Our":[106],"method":[107],"able":[109],"abstractions":[112],"locomotive":[114],"optimal":[116],"control":[117],"tasks":[118],"increase":[120],"sample":[122],"efficiency":[123],"both":[125],"known":[126],"unknown":[128],"opening":[130],"path":[133],"endow":[135],"artificial":[136],"agents":[137],"with":[138],"generalization":[139],"abilities.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}