{"id":"https://openalex.org/W4382866759","doi":"https://doi.org/10.1609/icaps.v33i1.27197","title":"Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring","display_name":"Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4382866759","doi":"https://doi.org/10.1609/icaps.v33i1.27197"},"language":"en","primary_location":{"id":"doi:10.1609/icaps.v33i1.27197","is_oa":true,"landing_page_url":"https://doi.org/10.1609/icaps.v33i1.27197","pdf_url":"https://ojs.aaai.org/index.php/ICAPS/article/download/27197/26970","source":{"id":"https://openalex.org/S4387283601","display_name":"Proceedings of the International Conference on Automated Planning and Scheduling","issn_l":"2334-0835","issn":["2334-0835","2334-0843"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Automated Planning and Scheduling","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/ICAPS/article/download/27197/26970","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025698303","display_name":"Merlijn Krale","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Merlijn Krale","raw_affiliation_strings":["Radboud University, Nijmegen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035570774","display_name":"Thiago D. Sim\u00e3o","orcid":"https://orcid.org/0000-0002-3568-9464"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thiago D. Sim\u00e3o","raw_affiliation_strings":["Radboud University, Nijmegen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012669709","display_name":"Nils Jansen","orcid":"https://orcid.org/0000-0003-1318-8973"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nils Jansen","raw_affiliation_strings":["Radboud University, Nijmegen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen","institution_ids":["https://openalex.org/I145872427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145872427"],"apc_list":null,"apc_paid":null,"fwci":0.8199,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72826243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"33","issue":"1","first_page":"212","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.980400025844574,"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":0.980400025844574,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9092000126838684,"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":0.8392612338066101},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.8276134729385376},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7832923531532288},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.7824232578277588},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.750918984413147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7249858975410461},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6670214533805847},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6518577933311462},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5259395241737366},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5212993621826172},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44461068511009216},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4349738359451294},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40600013732910156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35042378306388855},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.26393240690231323},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24680912494659424},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19037744402885437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1716659665107727},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1269354522228241},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07342204451560974}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8392612338066101},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.8276134729385376},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7832923531532288},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.7824232578277588},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.750918984413147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249858975410461},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6670214533805847},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6518577933311462},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5259395241737366},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5212993621826172},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44461068511009216},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4349738359451294},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40600013732910156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35042378306388855},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.26393240690231323},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24680912494659424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19037744402885437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1716659665107727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1269354522228241},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07342204451560974},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/icaps.v33i1.27197","is_oa":true,"landing_page_url":"https://doi.org/10.1609/icaps.v33i1.27197","pdf_url":"https://ojs.aaai.org/index.php/ICAPS/article/download/27197/26970","source":{"id":"https://openalex.org/S4387283601","display_name":"Proceedings of the International Conference on Automated Planning and Scheduling","issn_l":"2334-0835","issn":["2334-0835","2334-0843"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Automated Planning and Scheduling","raw_type":"journal-article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/294785","is_oa":true,"landing_page_url":"https://hdl.handle.net/2066/294785","pdf_url":"https://repository.ubn.ru.nl//bitstream/handle/2066/294785/294785.pdf","source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article / Letter to editor"}],"best_oa_location":{"id":"doi:10.1609/icaps.v33i1.27197","is_oa":true,"landing_page_url":"https://doi.org/10.1609/icaps.v33i1.27197","pdf_url":"https://ojs.aaai.org/index.php/ICAPS/article/download/27197/26970","source":{"id":"https://openalex.org/S4387283601","display_name":"Proceedings of the International Conference on Automated Planning and Scheduling","issn_l":"2334-0835","issn":["2334-0835","2334-0843"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Automated Planning and Scheduling","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2039356335","display_name":null,"funder_award_id":"1160.18.238","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G4371345817","display_name":"PrimaVera: Predictive maintenance for Very effective asset management","funder_award_id":"NWA.1160.18.238","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382866759.pdf","grobid_xml":"https://content.openalex.org/works/W4382866759.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1496855202","https://openalex.org/W1539216098","https://openalex.org/W1657674574","https://openalex.org/W1782523431","https://openalex.org/W1973749650","https://openalex.org/W1980035368","https://openalex.org/W1997188340","https://openalex.org/W2124267516","https://openalex.org/W2161966552","https://openalex.org/W2171084228","https://openalex.org/W2284276045","https://openalex.org/W2907502549","https://openalex.org/W2950624398","https://openalex.org/W2964183049","https://openalex.org/W2978212076","https://openalex.org/W3011416673","https://openalex.org/W3017275226","https://openalex.org/W3019709472","https://openalex.org/W3028818653","https://openalex.org/W3095437761","https://openalex.org/W3102668249","https://openalex.org/W3121342653","https://openalex.org/W3174896399","https://openalex.org/W3211465897","https://openalex.org/W3216656735","https://openalex.org/W4280549236","https://openalex.org/W4285307725","https://openalex.org/W4288319859","https://openalex.org/W4289010281","https://openalex.org/W4292652755","https://openalex.org/W4293536486","https://openalex.org/W4382317716","https://openalex.org/W4382866759","https://openalex.org/W4385873144","https://openalex.org/W4394666657","https://openalex.org/W6629614444","https://openalex.org/W6684973485","https://openalex.org/W6695925467","https://openalex.org/W6708993328","https://openalex.org/W6767076659"],"related_works":["https://openalex.org/W2146763310","https://openalex.org/W1563041104","https://openalex.org/W4327667434","https://openalex.org/W2347690758","https://openalex.org/W2381909226","https://openalex.org/W3211465897","https://openalex.org/W1966071689","https://openalex.org/W2332673980","https://openalex.org/W1541084404","https://openalex.org/W1581055761"],"abstract_inverted_index":{"We":[0,84,107],"study":[1],"Markov":[2],"decision":[3],"processes":[4],"(MDPs),":[5],"where":[6],"agents":[7],"control":[8,31,68],"when":[9,66],"and":[10,39,97,127],"how":[11,35,86],"they":[12],"gather":[13],"information,":[14],"as":[15],"formalized":[16],"by":[17],"action-contingent":[18],"noiselessly":[19],"observable":[20,125],"MDPs":[21],"(ACNO-MPDs).":[22],"In":[23],"these":[24],"models,":[25],"actions":[26],"have":[27],"two":[28],"components:":[29],"a":[30,40,99,109,119,137],"action":[32,42],"that":[33,43,59],"influences":[34],"the":[36,45,53,79,102,115],"environment":[37],"changes":[38],"measurement":[41],"affects":[44],"agent's":[46],"observation.":[47],"To":[48,70],"solve":[49],"ACNO-MDPs,":[50],"we":[51,60,77],"introduce":[52,78],"act-then-measure":[54],"(ATM)":[55],"heuristic,":[56,117],"which":[57],"assumes":[58],"can":[61],"ignore":[62],"future":[63],"state":[64],"uncertainty":[65],"choosing":[67],"actions.":[69],"decide":[71],"whether":[72],"or":[73],"not":[74],"to":[75,92,133],"measure,":[76],"concept":[80],"of":[81,139],"measuring":[82],"value.":[83],"show":[85],"following":[87],"this":[88],"heuristic":[89],"may":[90],"lead":[91],"shorter":[93],"policy":[94],"computation":[95],"times":[96],"prove":[98],"bound":[100],"on":[101,114,136],"performance":[103,131],"loss":[104],"it":[105],"incurs.":[106],"develop":[108],"reinforcement":[110],"learning":[111],"algorithm":[112],"based":[113],"ATM":[116],"using":[118],"Dyna-Q":[120],"variant":[121],"adapted":[122],"for":[123],"partially":[124],"domains,":[126],"showcase":[128],"its":[129],"superior":[130],"compared":[132],"prior":[134],"methods":[135],"number":[138],"partially-observable":[140],"environments.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-09-08T07:41:39.490200","created_date":"2025-10-10T00:00:00"}