{"id":"https://openalex.org/W4285102131","doi":"https://doi.org/10.1109/icra46639.2022.9812262","title":"Scalable Gradient Ascent for Controllers in Constrained POMDPs","display_name":"Scalable Gradient Ascent for Controllers in Constrained POMDPs","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285102131","doi":"https://doi.org/10.1109/icra46639.2022.9812262"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812262","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","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/A5013249239","display_name":"Kyle Hollins Wray","orcid":"https://orcid.org/0000-0001-6986-9941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyle Hollins Wray","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029567541","display_name":"Kenneth Czuprynski","orcid":"https://orcid.org/0000-0001-8926-6945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenneth Czuprynski","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":6,"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":0.9997000098228455,"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":0.9997000098228455,"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/T12288","display_name":"Optimization and Search Problems","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9907000064849854,"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":0.6322121024131775},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5845736861228943},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5568811297416687},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5514642596244812},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5459550619125366},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5442876815795898},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5339943766593933},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5211160778999329},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.48767364025115967},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48023468255996704},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4791949689388275},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4413202702999115},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4125061333179474},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.347259521484375},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2584259510040283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2243240475654602},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2048751711845398},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06999945640563965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6322121024131775},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5845736861228943},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5568811297416687},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5514642596244812},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5459550619125366},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5442876815795898},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5339943766593933},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5211160778999329},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.48767364025115967},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48023468255996704},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4791949689388275},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4413202702999115},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4125061333179474},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.347259521484375},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2584259510040283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2243240475654602},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2048751711845398},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06999945640563965},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9812262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812262","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494689917","https://openalex.org/W1503109067","https://openalex.org/W1701684472","https://openalex.org/W2087992130","https://openalex.org/W2102660061","https://openalex.org/W2107770641","https://openalex.org/W2110962519","https://openalex.org/W2119852681","https://openalex.org/W2168359464","https://openalex.org/W2219400200","https://openalex.org/W2259075191","https://openalex.org/W2572445540","https://openalex.org/W2739957299","https://openalex.org/W2788292202","https://openalex.org/W3161533801","https://openalex.org/W3205460851","https://openalex.org/W6629836980","https://openalex.org/W6629917913","https://openalex.org/W6637465547","https://openalex.org/W6678181239","https://openalex.org/W6692580597","https://openalex.org/W6731636634"],"related_works":["https://openalex.org/W2404647514","https://openalex.org/W1667647204","https://openalex.org/W4247536566","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W4241418540","https://openalex.org/W1508895727","https://openalex.org/W158195847","https://openalex.org/W2285068904","https://openalex.org/W2068568378"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,34,101,105],"novel":[4,77,92],"gradient":[5,30],"ascent":[6,31],"al-gorithm":[7],"and":[8,45,58,69,76],"nonlinear":[9],"programming":[10],"algorithm":[11,32,57,70,93],"for":[12],"finite":[13],"state":[14],"controller":[15],"policies":[16],"in":[17,104],"constrained":[18],"partially":[19],"observable":[20],"Markov":[21],"decision":[22],"processes":[23],"(CPOMDPs).":[24],"A":[25,52],"key":[26],"component":[27],"of":[28,55,66],"the":[29,56,74],"is":[33,61,94],"constraint":[35,83],"projection":[36,48,67],"to":[37],"ensure":[38],"constraints":[39],"are":[40,49],"satisfied.":[41],"Both":[42],"an":[43,46,97],"optimal":[44],"approximate":[47],"formally":[50,63],"defined.":[51],"theoretical":[53],"analysis":[54],"its":[59],"projections":[60],"presented,":[62],"proving":[64],"aspects":[65],"correctness":[68],"convergence.":[71],"Experiments":[72],"evaluate":[73],"baseline":[75],"algorithms,":[78],"as":[79,81],"well":[80],"both":[82],"projections,":[84],"on":[85,96],"seven":[86],"CPOMDP":[87],"benchmark":[88],"domains.":[89],"The":[90],"proposed":[91],"demonstrated":[95],"actual":[98],"robot":[99],"performing":[100],"navigation":[102],"task":[103],"real":[106],"household":[107],"environment.":[108]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}