{"id":"https://openalex.org/W1563254111","doi":"https://doi.org/10.1109/ijcnn.2005.1556399","title":"An analysis of gradient-based policy iteration","display_name":"An analysis of gradient-based policy iteration","publication_year":2006,"publication_date":"2006-01-05","ids":{"openalex":"https://openalex.org/W1563254111","doi":"https://doi.org/10.1109/ijcnn.2005.1556399","mag":"1563254111"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2005.1556399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2005.1556399","pdf_url":null,"source":{"id":"https://openalex.org/S4363609022","display_name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","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. 2005 IEEE International Joint Conference on Neural Networks, 2005.","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/A5073315467","display_name":"James Dankert","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"J. Dankert","raw_affiliation_strings":["Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","Dept. of Electr. Eng.. Arizona State Univ., Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Dept. of Electr. Eng.. Arizona State Univ., Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072565301","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-5176-003X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","Dept. of Electr. Eng.. Arizona State Univ., Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Dept. of Electr. Eng.. Arizona State Univ., Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085653399","display_name":"Jennie Si","orcid":"https://orcid.org/0000-0002-0374-7404"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Si","raw_affiliation_strings":["Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","Dept. of Electr. Eng.. Arizona State Univ., Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Dept. of Electr. Eng.. Arizona State Univ., Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073315467"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11913104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"2977","last_page":"2982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940000176429749,"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":0.9940000176429749,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9266999959945679,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9255187511444092},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7888693809509277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6757060885429382},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6590468883514404},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6361063122749329},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6317819952964783},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5540977120399475},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5433254241943359},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.46226656436920166},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.45712608098983765},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4241180121898651},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4130650758743286},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2601403295993805},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24886438250541687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2365487813949585},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13146567344665527}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.9255187511444092},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7888693809509277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6757060885429382},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6590468883514404},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6361063122749329},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6317819952964783},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5540977120399475},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5433254241943359},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.46226656436920166},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.45712608098983765},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4241180121898651},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4130650758743286},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2601403295993805},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24886438250541687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2365487813949585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13146567344665527},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2005.1556399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2005.1556399","pdf_url":null,"source":{"id":"https://openalex.org/S4363609022","display_name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","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. 2005 IEEE International Joint Conference on Neural Networks, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1517613402","https://openalex.org/W1541084404","https://openalex.org/W1794980568","https://openalex.org/W2098432798","https://openalex.org/W2147607210","https://openalex.org/W2334782222","https://openalex.org/W4297744580","https://openalex.org/W4300306656","https://openalex.org/W6631055690"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W2364406457","https://openalex.org/W2173087131","https://openalex.org/W1997350370","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Recently,":[0],"a":[1,39],"system":[2,36],"theoretic":[3,37],"framework":[4],"for":[5],"learning":[6,29],"and":[7,27,78],"optimization":[8,41],"has":[9,48],"been":[10,49],"developed":[11],"that":[12,80],"shows":[13],"how":[14,56],"many":[15],"approximate":[16],"dynamic":[17],"programming":[18],"paradigms":[19],"such":[20],"as":[21],"perturbation":[22],"analysis,":[23],"Markov":[24,65],"decision":[25,66],"processes,":[26],"reinforcement":[28],"are":[30],"very":[31],"closely":[32],"related.":[33],"Using":[34],"this":[35,52,81],"framework,":[38],"new":[40,82],"technique":[42],"called":[43],"gradient-based":[44],"policy":[45],"iteration":[46,58,74,96],"(GBPI)":[47],"developed.":[50],"In":[51],"paper,":[53],"we":[54],"show":[55,79],"GBPI":[57,77],"can":[59],"be":[60],"extended":[61,87],"to":[62,88],"partially":[63],"observable":[64],"processes":[67],"(POMDPs).":[68],"We":[69],"also":[70,98],"develop":[71],"the":[72],"value":[73,85,95],"analogue":[75],"of":[76,84],"version":[83],"iteration,":[86],"POMDPs,":[89],"not":[90],"only":[91],"theoretically":[92],"acts":[93],"like":[94],"but":[97],"does":[99],"so":[100],"numerically.":[101]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}