{"id":"https://openalex.org/W4416252353","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228072","title":"OCMDP: Observation-Constrained Markov Decision Process","display_name":"OCMDP: Observation-Constrained Markov Decision Process","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252353","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228072"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5054326240","display_name":"Taiyi Wang","orcid":"https://orcid.org/0000-0002-5933-6866"},"institutions":[{"id":"https://openalex.org/I4210165075","display_name":"National Power (United Kingdom)","ror":"https://ror.org/05rnt2n49","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210165075"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Taiyi Wang","raw_affiliation_strings":["Powersense Technology Limited"],"affiliations":[{"raw_affiliation_string":"Powersense Technology Limited","institution_ids":["https://openalex.org/I4210165075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037555693","display_name":"Jianheng Liu","orcid":"https://orcid.org/0000-0002-3124-5559"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianheng Liu","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041965133","display_name":"Bryan S. Lee","orcid":"https://orcid.org/0000-0002-2601-5783"},"institutions":[{"id":"https://openalex.org/I4210165075","display_name":"National Power (United Kingdom)","ror":"https://ror.org/05rnt2n49","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210165075"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bryan Lee","raw_affiliation_strings":["Powersense Technology Limited"],"affiliations":[{"raw_affiliation_string":"Powersense Technology Limited","institution_ids":["https://openalex.org/I4210165075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119247518","display_name":"Zhihao Wu","orcid":"https://orcid.org/0000-0003-1602-742X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhihao Wu","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039970749","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0003-0139-8105"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["University of Cambridge"],"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054326240"],"corresponding_institution_ids":["https://openalex.org/I4210165075"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19528943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.49070000648498535,"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":0.49070000648498535,"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":0.07010000199079514,"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":0.06790000200271606,"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/markov-decision-process","display_name":"Markov decision process","score":0.7757999897003174},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.7002000212669373},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6294000148773193},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6025999784469604},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5199000239372253},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.47870001196861267},{"id":"https://openalex.org/keywords/process-control","display_name":"Process control","score":0.3901999890804291},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3815999925136566}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7757999897003174},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607999801635742},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6294000148773193},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6025999784469604},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4925000071525574},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4659000039100647},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.3901999890804291},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":16,"referenced_works":["https://openalex.org/W52153049","https://openalex.org/W1918371733","https://openalex.org/W2168359464","https://openalex.org/W2557738935","https://openalex.org/W2581082771","https://openalex.org/W2905810301","https://openalex.org/W2934399013","https://openalex.org/W2951360122","https://openalex.org/W3120101765","https://openalex.org/W3126970305","https://openalex.org/W3174896399","https://openalex.org/W4200117349","https://openalex.org/W4239466562","https://openalex.org/W4301895924","https://openalex.org/W4394776858","https://openalex.org/W4403742889"],"related_works":[],"abstract_inverted_index":{"In":[0],"many":[1],"practical":[2],"applications,":[3],"decision-making":[4],"processes":[5],"must":[6],"balance":[7],"the":[8,14,34,49,56,59,62,67,71,88,94,102,125],"costs":[9,144],"of":[10,36,61,93,124],"acquiring":[11],"information":[12],"with":[13],"benefits":[15],"it":[16],"provides.":[17],"Traditional":[18],"control":[19,41,75,91,119],"systems":[20],"often":[21],"assume":[22],"full":[23],"observability,":[24],"an":[25,79],"unrealistic":[26],"assumption":[27],"when":[28,109],"observations":[29],"are":[30],"expensive.":[31],"We":[32],"tackle":[33],"challenge":[35],"simultaneously":[37],"learning":[38,84,100],"observation":[39,73,143],"and":[40,74,90,110,134],"strategies":[42],"in":[43,101,150],"such":[44],"cost-sensitive":[45],"environments":[46,135],"by":[47,106],"introducing":[48],"Observation-Constrained":[50],"Markov":[51],"Decision":[52],"Process":[53],"(OCMDP),":[54],"where":[55],"policy":[57],"influences":[58],"observability":[60],"true":[63],"state.":[64],"To":[65],"manage":[66],"complexity":[68],"arising":[69],"from":[70],"combined":[72],"actions,":[76,120],"we":[77],"develop":[78],"iterative,":[80],"model-free":[81],"deep":[82],"reinforcement":[83],"algorithm":[85],"that":[86,137],"separates":[87],"sensing":[89],"components":[92],"policy.":[95],"This":[96],"decomposition":[97],"enables":[98],"efficient":[99],"expanded":[103],"action":[104],"space":[105],"focusing":[107],"on":[108],"what":[111],"to":[112],"observe,":[113],"as":[114,116],"well":[115],"determining":[117],"optimal":[118],"without":[121],"requiring":[122],"knowledge":[123],"environment\u2019s":[126],"dynamics.":[127],"Experimental":[128],"results":[129],"across":[130,152],"diverse":[131],"healthcare":[132],"tasks":[133],"demonstrate":[136],"our":[138],"proposed":[139],"approach":[140],"substantially":[141],"reduces":[142],"while":[145],"significantly":[146],"outperforming":[147],"baseline":[148],"methods":[149],"efficiency":[151],"various":[153],"real-world":[154],"scenarios.":[155]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}