{"id":"https://openalex.org/W2996651463","doi":"https://doi.org/10.1109/smc.2019.8913930","title":"MDP Autoencoder","display_name":"MDP Autoencoder","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2996651463","doi":"https://doi.org/10.1109/smc.2019.8913930","mag":"2996651463"},"language":"en","primary_location":{"id":"doi:10.1109/smc.2019.8913930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2019.8913930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030977697","display_name":"Sourabh Bose","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sourabh Bose","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047174917","display_name":"Manfred Huber","orcid":"https://orcid.org/0009-0007-0294-9147"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manfred Huber","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"2899","last_page":"2906"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9740999937057495,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9528999924659729,"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":0.8587692975997925},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.7902234792709351},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7404053807258606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7356215715408325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6770944595336914},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4832340180873871},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48208552598953247},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.46243393421173096},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4378195106983185},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.41807636618614197},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.41008269786834717},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2702721655368805},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12785103917121887}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8587692975997925},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7902234792709351},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7404053807258606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7356215715408325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6770944595336914},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4832340180873871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48208552598953247},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.46243393421173096},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4378195106983185},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41807636618614197},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.41008269786834717},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2702721655368805},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12785103917121887},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc.2019.8913930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2019.8913930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)","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":44,"referenced_works":["https://openalex.org/W10548402","https://openalex.org/W13310149","https://openalex.org/W36691172","https://openalex.org/W41554520","https://openalex.org/W834081922","https://openalex.org/W1553182805","https://openalex.org/W1757796397","https://openalex.org/W1959608418","https://openalex.org/W2034806191","https://openalex.org/W2099471712","https://openalex.org/W2105960367","https://openalex.org/W2118688707","https://openalex.org/W2121863487","https://openalex.org/W2166618252","https://openalex.org/W2191938486","https://openalex.org/W2547875792","https://openalex.org/W2920362155","https://openalex.org/W2962841471","https://openalex.org/W2963430173","https://openalex.org/W2963629403","https://openalex.org/W2964077562","https://openalex.org/W2964167449","https://openalex.org/W2964220198","https://openalex.org/W3021208093","https://openalex.org/W4289294484","https://openalex.org/W4297789121","https://openalex.org/W4298857966","https://openalex.org/W4320013936","https://openalex.org/W6600544951","https://openalex.org/W6601473733","https://openalex.org/W6623316541","https://openalex.org/W6633100451","https://openalex.org/W6637967152","https://openalex.org/W6640963894","https://openalex.org/W6675715384","https://openalex.org/W6677477928","https://openalex.org/W6687386564","https://openalex.org/W6687506355","https://openalex.org/W6728805014","https://openalex.org/W6729448088","https://openalex.org/W6740836278","https://openalex.org/W6756256016","https://openalex.org/W6760405395","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2372020181","https://openalex.org/W2156531654","https://openalex.org/W1581723585","https://openalex.org/W4378714697","https://openalex.org/W2294330161","https://openalex.org/W2940472653","https://openalex.org/W2253069048","https://openalex.org/W2804553224","https://openalex.org/W140709781","https://openalex.org/W3214340375"],"abstract_inverted_index":{"This":[0,74],"paper":[1],"proposes":[2],"a":[3,12,77],"novel":[4],"deep":[5],"reinforcement":[6,47],"learning":[7,48],"(RL)":[8],"architecture,":[9],"which":[10,106],"learns":[11,97],"dynamics":[13,86],"model":[14,45,80],"in":[15,39,76],"latent":[16,55,99],"space":[17,25],"that":[18,81,93,102],"is":[19],"behaviorally":[20],"grounded":[21],"to":[22,33,43,110],"the":[23,28,37,53,59,71,84,88,94],"observed":[24,89],"and":[26,61],"applies":[27],"framework":[29],"of":[30,63,69,87],"MDP":[31],"homomorphisms":[32],"provide":[34],"bounds":[35],"for":[36],"loss":[38],"performance.":[40],"In":[41],"contrast":[42],"traditional":[44],"based":[46],"algorithms,":[49],"this":[50],"approach":[51,96],"models":[52,101],"next":[54],"state":[56],"while":[57],"predicting":[58],"rewards":[60],"chance":[62],"termination":[64],"after":[65],"current":[66],"step,":[67],"instead":[68],"reconstructing":[70],"future":[72],"observations.":[73],"results":[75],"much":[78],"simpler":[79],"can":[82,103],"encode":[83,104],"underlying":[85],"system.":[90],"Experiments":[91],"show":[92],"proposed":[95],"concise":[98],"Markov":[100],"policies":[105],"achieve":[107],"scores":[108],"close":[109],"optimal.":[111]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-12-26T00:00:00"}