{"id":"https://openalex.org/W2560154784","doi":"https://doi.org/10.48550/arxiv.1612.00475","title":"Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes","display_name":"Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2560154784","doi":"https://doi.org/10.48550/arxiv.1612.00475","mag":"2560154784"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1612.00475","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.00475","pdf_url":"https://arxiv.org/pdf/1612.00475","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1612.00475","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007476482","display_name":"Taylor W. Killian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Killian, Taylor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078124517","display_name":"George Konidaris","orcid":"https://orcid.org/0000-0002-4460-2519","observed_orcids":["https://orcid.org/0000-0002-4460-2519"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konidaris, George","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038771285","display_name":"Finale Doshi\u2010Velez","orcid":"https://orcid.org/0000-0003-2886-3898","observed_orcids":["https://orcid.org/0000-0003-2886-3898"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doshi-Velez, Finale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7275000214576721,"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":0.7275000214576721,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.06520000100135803,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.024299999698996544,"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/transfer-learning","display_name":"transfer learning","score":0.9110000133514404},{"id":"https://openalex.org/keywords/patient-heterogeneity","display_name":"patient heterogeneity","score":0.6489999890327454},{"id":"https://openalex.org/keywords/personalized-medicine","display_name":"personalized medicine","score":0.746999979019165},{"id":"https://openalex.org/keywords/hiv-treatment","display_name":"HIV treatment","score":0.9589999914169312},{"id":"https://openalex.org/keywords/state-uncertainty","display_name":"state uncertainty","score":0.8970000147819519},{"id":"https://openalex.org/keywords/human-robot-interaction","display_name":"human-robot interaction","score":0.5720000267028809},{"id":"https://openalex.org/keywords/treatment-response-variability","display_name":"treatment response variability","score":0.5009999871253967}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7977044582366943},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7473567724227905},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6051117181777954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5912893414497375},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5697352886199951},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5100834965705872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5054605007171631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.495173841714859},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44038793444633484},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4390637278556824},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3713318705558777},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24458587169647217},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10602039098739624},{"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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1612.00475","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.00475","pdf_url":"https://arxiv.org/pdf/1612.00475","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1612.00475","doi":"https://doi.org/10.48550/arxiv.1612.00475","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1612.00475","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1612.00475","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.00475","pdf_url":"https://arxiv.org/pdf/1612.00475","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.6240000128746033}],"sustainable_development_goals_aurora":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.800000011920929}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W66188587","https://openalex.org/W1603035390","https://openalex.org/W1757796397","https://openalex.org/W1825573441","https://openalex.org/W2018705428","https://openalex.org/W2095897186","https://openalex.org/W2099768828","https://openalex.org/W2103535498","https://openalex.org/W2120346334","https://openalex.org/W2135721773","https://openalex.org/W2140135625","https://openalex.org/W2151161180","https://openalex.org/W2151268438","https://openalex.org/W2155968351","https://openalex.org/W2166063021","https://openalex.org/W2168359464","https://openalex.org/W2169779569","https://openalex.org/W2199530954","https://openalex.org/W2201581102","https://openalex.org/W2333635821","https://openalex.org/W2464224693","https://openalex.org/W2564513914"],"related_works":["https://openalex.org/W4388236136","https://openalex.org/W2807018115","https://openalex.org/W4200250224","https://openalex.org/W2126560268","https://openalex.org/W2285658092","https://openalex.org/W187740018","https://openalex.org/W2482498454","https://openalex.org/W2162286586","https://openalex.org/W2947128950","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Due":[0],"to":[1,16,81,97],"physiological":[2],"variation,":[3],"patients":[4],"diagnosed":[5],"with":[6],"the":[7,17,39,48,55,72,91],"same":[8,18],"condition":[9],"may":[10],"exhibit":[11],"divergent,":[12],"but":[13],"related,":[14],"responses":[15],"treatments.":[19],"Hidden":[20],"Parameter":[21],"Markov":[22],"Decision":[23],"Processes":[24],"(HiP-MDPs)":[25],"tackle":[26],"this":[27],"transfer-learning":[28],"problem":[29],"by":[30],"embedding":[31,49],"these":[32],"tasks":[33,67],"into":[34],"a":[35,45,82],"low-dimensional":[36],"space.":[37],"However,":[38],"original":[40],"formulation":[41],"of":[42,54,71],"HiP-MDP":[43,92],"had":[44],"critical":[46],"flaw:":[47],"uncertainty":[50],"was":[51],"modeled":[52],"independently":[53],"agent's":[56],"state":[57,73],"uncertainty,":[58],"requiring":[59],"an":[60],"unnatural":[61],"training":[62],"procedure":[63],"in":[64],"which":[65],"all":[66],"visited":[68],"every":[69],"part":[70],"space---possible":[74],"for":[75,86,104],"robots":[76],"that":[77],"can":[78],"be":[79],"moved":[80],"particular":[83],"location,":[84],"impossible":[85],"human":[87],"patients.":[88],"We":[89],"update":[90],"framework":[93],"and":[94],"extend":[95],"it":[96],"more":[98],"robustly":[99],"develop":[100],"personalized":[101],"medicine":[102],"strategies":[103],"HIV":[105],"treatment.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-12-16T00:00:00"}