{"id":"https://openalex.org/W2128749571","doi":"https://doi.org/10.1109/icsmc.2004.1401080","title":"Incremental topological reinforcement learning agent in non-structured environments","display_name":"Incremental topological reinforcement learning agent in non-structured environments","publication_year":2005,"publication_date":"2005-03-31","ids":{"openalex":"https://openalex.org/W2128749571","doi":"https://doi.org/10.1109/icsmc.2004.1401080","mag":"2128749571"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2004.1401080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1401080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","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/A5087507919","display_name":"Arthur P. S. Braga","orcid":"https://orcid.org/0000-0002-7776-7264"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"A.P. de S. Braga","raw_affiliation_strings":["Electrical Engineering Department, University of S\u00e3o Paulo, Sao Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, University of S\u00e3o Paulo, Sao Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029986478","display_name":"A.F.R. Araujo","orcid":null},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"A.F.R. Araujo","raw_affiliation_strings":["Computer Science Department, Pemambuco Federal University, Recife, Pernambuco, Brazil"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Pemambuco Federal University, Recife, Pernambuco, Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069031865","display_name":"Jeremy Wyatt","orcid":"https://orcid.org/0000-0001-6991-356X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Wyatt","raw_affiliation_strings":["School of Computer Science, University of Binningham, Birmingham, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Binningham, Birmingham, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087507919"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":0.4387,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74787823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"5567","last_page":"5572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9993000030517578,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.9148877859115601},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.907686173915863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.732359766960144},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6508581042289734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5438618659973145},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5231874585151672},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.521895706653595},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5041714906692505},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.498096227645874},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.43988433480262756},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4059281647205353},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.39788565039634705},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.26724061369895935},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1429494321346283},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11869704723358154},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06631043553352356}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9148877859115601},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.907686173915863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732359766960144},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6508581042289734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5438618659973145},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5231874585151672},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.521895706653595},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5041714906692505},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.498096227645874},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.43988433480262756},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4059281647205353},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.39788565039634705},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.26724061369895935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1429494321346283},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11869704723358154},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06631043553352356},{"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/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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2004.1401080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1401080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","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":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W139877375","https://openalex.org/W1488696015","https://openalex.org/W1531900088","https://openalex.org/W1549519846","https://openalex.org/W1583882820","https://openalex.org/W1601378499","https://openalex.org/W1716092612","https://openalex.org/W1980035368","https://openalex.org/W1982948368","https://openalex.org/W2029130131","https://openalex.org/W2035808435","https://openalex.org/W2041126907","https://openalex.org/W2088359268","https://openalex.org/W2100675387","https://openalex.org/W2107726111","https://openalex.org/W2126009268","https://openalex.org/W2154727892","https://openalex.org/W2610686804","https://openalex.org/W3011120880","https://openalex.org/W3036512766","https://openalex.org/W4214717370","https://openalex.org/W6675410042"],"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/W3096874164","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,93],"new":[4],"reinforcement":[5,12],"learning":[6,13],"(RL)":[7],"model,":[8],"the":[9,56,80,85],"incremental":[10],"topological":[11],"agent":[14,19],"(ITRLA),":[15],"designed":[16],"to":[17,47,55,83],"guide":[18],"navigation":[20],"in":[21,38,42,89],"non-structured":[22,43,90],"environments,":[23],"considering":[24],"two":[25,86],"common":[26],"situations:":[27],"(i)":[28],"insertion":[29],"of":[30,79,96],"noise":[31],"during":[32],"state":[33,58],"estimation":[34],"and":[35,98],"(ii)":[36],"changes":[37],"environment":[39],"structure.":[40],"Tasks":[41],"environments":[44,91],"are":[45,62],"hard":[46],"be":[48],"learned":[49],"by":[50],"traditional":[51],"RL":[52],"algorithms":[53],"due":[54],"stochastic":[57],"transitions.":[59],"Such":[60],"tasks":[61],"often":[63],"modeled":[64],"as":[65],"partially":[66],"observable":[67],"Markov":[68],"decision":[69],"processes":[70],"(POMDP),":[71],"an":[72],"expensive":[73],"computational":[74],"process.":[75],"The":[76],"main":[77],"contribution":[78],"ITRLA":[81],"is":[82],"handle":[84],"mentioned":[87],"situations":[88],"with":[92],"reduced":[94],"number":[95],"trials,":[97],"avoiding":[99],"POMDP":[100],"modeling.":[101]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}