{"id":"https://openalex.org/W4229017439","doi":"https://doi.org/10.1145/3477314.3507049","title":"Learning state-variable relationships for improving POMCP performance","display_name":"Learning state-variable relationships for improving POMCP performance","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4229017439","doi":"https://doi.org/10.1145/3477314.3507049"},"language":"en","primary_location":{"id":"doi:10.1145/3477314.3507049","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507049","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","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/A5032950613","display_name":"Maddalena Zuccotto","orcid":null},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Maddalena Zuccotto","raw_affiliation_strings":["University of Verona, Verona, Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078441040","display_name":"Alberto Castellini","orcid":"https://orcid.org/0000-0001-8420-0699"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Castellini","raw_affiliation_strings":["University of Verona, Verona, Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045922629","display_name":"Alessandro Farinelli","orcid":"https://orcid.org/0000-0002-2592-5814"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Farinelli","raw_affiliation_strings":["University of Verona, Verona, Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032950613"],"corresponding_institution_ids":["https://openalex.org/I119439378"],"apc_list":null,"apc_paid":null,"fwci":0.4155,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55602241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"739","last_page":"747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9952999949455261,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9952999949455261,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9908999800682068,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9890999794006348,"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":0.759728193283081},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6919898986816406},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.6547914743423462},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6466009616851807},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6370839476585388},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5841017961502075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.581030547618866},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5568234324455261},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5489136576652527},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.5432409644126892},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5239841341972351},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5119608640670776},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4744478464126587},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4610336124897003},{"id":"https://openalex.org/keywords/state-variable","display_name":"State variable","score":0.4561942219734192},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4275391101837158},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.3542611598968506},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3317888379096985},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22942745685577393},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13634437322616577},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07526683807373047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759728193283081},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6919898986816406},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.6547914743423462},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6466009616851807},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6370839476585388},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5841017961502075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.581030547618866},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5568234324455261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5489136576652527},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.5432409644126892},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5239841341972351},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5119608640670776},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4744478464126587},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4610336124897003},{"id":"https://openalex.org/C129537906","wikidata":"https://www.wikidata.org/wiki/Q7603913","display_name":"State variable","level":2,"score":0.4561942219734192},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4275391101837158},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3542611598968506},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3317888379096985},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22942745685577393},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13634437322616577},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07526683807373047},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3477314.3507049","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507049","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1503398984","https://openalex.org/W1506806321","https://openalex.org/W1625390266","https://openalex.org/W2044375425","https://openalex.org/W2053476892","https://openalex.org/W2126316555","https://openalex.org/W2134802714","https://openalex.org/W2147071755","https://openalex.org/W2168359464","https://openalex.org/W2333931646","https://openalex.org/W2426452510","https://openalex.org/W2913668833","https://openalex.org/W2965902953","https://openalex.org/W3004707083","https://openalex.org/W3119977777","https://openalex.org/W3183479207","https://openalex.org/W4234669218","https://openalex.org/W4310895557"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"We":[0,43,81],"address":[1],"the":[2,35,53,57,69,72,76,90,96,105],"problem":[3],"of":[4,71],"learning":[5,97],"state-variable":[6,112],"relationships":[7],"across":[8],"different":[9,46],"episodes":[10],"in":[11,56],"Partially":[12,26],"Observable":[13,27],"Markov":[14,39],"Decision":[15],"Processes":[16],"(POMDPs)":[17],"to":[18,48,87,109,116],"improve":[19],"planning":[20],"performance.":[21],"Specifically,":[22],"we":[23,33],"focus":[24],"on":[25],"Monte":[28],"Carlo":[29],"Planning":[30],"(POMCP)":[31],"and":[32,67,95,115],"represent":[34],"acquired":[36,78],"knowledge":[37,77],"with":[38,120],"Random":[40],"Fields":[41],"(MRFs).":[42],"propose":[44,83],"three":[45],"methods":[47],"compute":[49],"MRF":[50,91],"parameters":[51],"while":[52],"agent":[54,64],"acts":[55],"environment.":[58],"Our":[59],"techniques":[60],"acquire":[61],"information":[62],"from":[63,68,79],"action":[65],"outcomes,":[66],"belief":[70],"agent,":[73],"which":[74],"summarizes":[75],"observations.":[80],"also":[82],"a":[84],"stopping":[85],"criterion":[86],"determine":[88],"when":[89],"is":[92],"accurate":[93],"enough":[94],"process":[98],"can":[99],"be":[100],"stopped.":[101],"Results":[102],"show":[103],"that":[104],"proposed":[106],"approach":[107],"allows":[108],"effectively":[110],"learn":[111],"probabilistic":[113],"constraints":[114],"outperform":[117],"standard":[118],"POMCP":[119],"no":[121],"computational":[122],"overhead.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}