{"id":"https://openalex.org/W4313496187","doi":"https://doi.org/10.1109/lars/sbr/wre56824.2022.9996033","title":"Memory-based Deep Reinforcement Learning for Humanoid Locomotion under Noisy Scenarios","display_name":"Memory-based Deep Reinforcement Learning for Humanoid Locomotion under Noisy Scenarios","publication_year":2022,"publication_date":"2022-10-18","ids":{"openalex":"https://openalex.org/W4313496187","doi":"https://doi.org/10.1109/lars/sbr/wre56824.2022.9996033"},"language":"en","primary_location":{"id":"doi:10.1109/lars/sbr/wre56824.2022.9996033","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lars/sbr/wre56824.2022.9996033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Latin American Robotics Symposium (LARS), 2022 Brazilian Symposium on Robotics (SBR), and 2022 Workshop on Robotics in Education (WRE)","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/A5091464812","display_name":"Samuel Chenatti","orcid":null},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Samuel Chenatti","raw_affiliation_strings":["Institute of Computing, University of Campinas,Laboratory of Robotics and Cognitive Systems (LaRoCS),São Paulo,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing, University of Campinas,Laboratory of Robotics and Cognitive Systems (LaRoCS),São Paulo,Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011531387","display_name":"Esther Luna Colombini","orcid":"https://orcid.org/0000-0003-0467-3133"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Esther L. Colombini","raw_affiliation_strings":["Institute of Computing, University of Campinas,Laboratory of Robotics and Cognitive Systems (LaRoCS),São Paulo,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing, University of Campinas,Laboratory of Robotics and Cognitive Systems (LaRoCS),São Paulo,Brazil","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181391015"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18697223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1707 2286","issue":null,"first_page":"205","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9889000058174133,"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":0.9889000058174133,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8541778326034546},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.8529199361801147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.801325261592865},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7439310550689697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6553674936294556},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6147879362106323},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5837074518203735},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5430646538734436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.417845755815506},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.26418203115463257},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.25911521911621094},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.18564698100090027},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12588003277778625}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8541778326034546},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.8529199361801147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.801325261592865},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7439310550689697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6553674936294556},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6147879362106323},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5837074518203735},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5430646538734436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.417845755815506},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.26418203115463257},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.25911521911621094},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.18564698100090027},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12588003277778625},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lars/sbr/wre56824.2022.9996033","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lars/sbr/wre56824.2022.9996033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Latin American Robotics Symposium (LARS), 2022 Brazilian Symposium on Robotics (SBR), and 2022 Workshop on Robotics in Education (WRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"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/G7557845564","display_name":null,"funder_award_id":"315468/2021-1","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1571143165","https://openalex.org/W2064675550","https://openalex.org/W2121092017","https://openalex.org/W2159498728","https://openalex.org/W2726187156","https://openalex.org/W2743645497","https://openalex.org/W2781726626","https://openalex.org/W2907877674","https://openalex.org/W2909718913","https://openalex.org/W2914838171","https://openalex.org/W2924656332","https://openalex.org/W2954718200","https://openalex.org/W2963184939","https://openalex.org/W3108412994","https://openalex.org/W3112664346","https://openalex.org/W3120364637","https://openalex.org/W3147852756","https://openalex.org/W3204535492","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W6683537259","https://openalex.org/W6740222838","https://openalex.org/W6742339999","https://openalex.org/W6747473740","https://openalex.org/W6757714754","https://openalex.org/W6760951303","https://openalex.org/W6764769363","https://openalex.org/W6786748177"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W1985560493","https://openalex.org/W2294884454","https://openalex.org/W2937181779"],"abstract_inverted_index":{"This":[0,54],"paper":[1],"proposes":[2],"a":[3,89,100],"model-free":[4,44],"memory":[5,67],"augmented":[6],"Deep":[7],"Reinforcement":[8],"Learning":[9],"(DRL)":[10],"method":[11],"that":[12,86],"can":[13,63],"deal":[14],"with":[15,43,104],"noisy":[16,49,110],"sensors":[17],"in":[18,32,47,99,108],"humanoid":[19,52],"locomotion.":[20],"DRL-based":[21],"agents":[22],"are":[23,38],"promising":[24],"for":[25,51,94],"automatically":[26],"learning":[27],"how":[28,57],"to":[29,72],"control":[30,45],"robots":[31],"complex":[33],"simulated":[34],"environments.":[35],"However,":[36],"they":[37],"still":[39],"not":[40],"fully":[41],"addressed":[42],"algorithms":[46],"challenging":[48],"scenarios":[50],"robots.":[53],"work":[55],"shows":[56],"the":[58,66,74,105],"Soft":[59],"Actor-Critic":[60],"(SAC)":[61],"algorithm":[62],"benefit":[64],"from":[65],"effect":[68],"introduced":[69],"by":[70,96],"LSTMs":[71],"mitigate":[73],"side":[75],"effects":[76],"of":[77],"Partially":[78],"Observed":[79],"Markov":[80],"Decision":[81],"Processes":[82],"(POMDP).":[83],"We":[84],"demonstrate":[85],"LSTM-SAC":[87],"is":[88],"viable":[90],"path":[91],"towards":[92],"DRL":[93],"POMDP":[95],"applying":[97],"it":[98],"bipedal":[101],"locomotion":[102],"task":[103],"NAO":[106],"Robot":[107],"various":[109],"scenarios.":[111]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}