{"id":"https://openalex.org/W4200140111","doi":"https://doi.org/10.1109/iros51168.2021.9636140","title":"Memory-based Deep Reinforcement Learning for POMDPs","display_name":"Memory-based Deep Reinforcement Learning for POMDPs","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W4200140111","doi":"https://doi.org/10.1109/iros51168.2021.9636140"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636140","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5048233348","display_name":"Lingheng Meng","orcid":"https://orcid.org/0000-0001-9419-5774"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lingheng Meng","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036605802","display_name":"Rob Gorbet","orcid":"https://orcid.org/0000-0003-2799-3922"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rob Gorbet","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072377971","display_name":"Dana Kuli\u0107","orcid":"https://orcid.org/0000-0002-4169-2141"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dana Kulic","raw_affiliation_strings":["Monash University, Melbourne, Victoria, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8347,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.97245841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5619","last_page":"5626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9909999966621399,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8632893562316895},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8061281442642212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7844831943511963},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.7152119278907776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6375501155853271},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6234225034713745},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5127745270729065},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.46007877588272095},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4578631520271301},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.43014878034591675},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42113375663757324},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4141642153263092},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3849051594734192},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.36365175247192383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35708725452423096},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.23653224110603333},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2357596755027771}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8632893562316895},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8061281442642212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7844831943511963},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.7152119278907776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6375501155853271},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6234225034713745},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5127745270729065},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.46007877588272095},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4578631520271301},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.43014878034591675},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42113375663757324},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4141642153263092},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3849051594734192},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.36365175247192383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35708725452423096},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.23653224110603333},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2357596755027771},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636140","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W51508254","https://openalex.org/W297984285","https://openalex.org/W1771410628","https://openalex.org/W1969554886","https://openalex.org/W1998376807","https://openalex.org/W2011418219","https://openalex.org/W2055921164","https://openalex.org/W2064675550","https://openalex.org/W2076337359","https://openalex.org/W2099541242","https://openalex.org/W2121092017","https://openalex.org/W2121615981","https://openalex.org/W2145339207","https://openalex.org/W2291973609","https://openalex.org/W2342662072","https://openalex.org/W2522489477","https://openalex.org/W2570651606","https://openalex.org/W2575705757","https://openalex.org/W2604216058","https://openalex.org/W2607713949","https://openalex.org/W2623293810","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2907052818","https://openalex.org/W2907916537","https://openalex.org/W2951941324","https://openalex.org/W2963428623","https://openalex.org/W2963454359","https://openalex.org/W2963864421","https://openalex.org/W3012388417","https://openalex.org/W3037042720","https://openalex.org/W4289285105","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6602057636","https://openalex.org/W6610758747","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6677939520","https://openalex.org/W6678087030","https://openalex.org/W6678317597","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6696783566","https://openalex.org/W6704571135","https://openalex.org/W6737069938","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6755305357","https://openalex.org/W6779841583"],"related_works":["https://openalex.org/W2999848267","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/W131709709","https://openalex.org/W2294884454","https://openalex.org/W3169161914"],"abstract_inverted_index":{"A":[0],"promising":[1],"characteristic":[2],"of":[3,48,61,119],"Deep":[4,88],"Reinforcement":[5],"Learning":[6],"(DRL)":[7],"is":[8,45,68],"its":[9,102],"capability":[10],"to":[11,75,98,129],"learn":[12],"optimal":[13],"policy":[14],"in":[15,108,123],"an":[16],"end-to-end":[17],"manner":[18],"without":[19],"relying":[20],"on":[21],"feature":[22],"engineering.":[23],"However,":[24],"most":[25],"approaches":[26],"assume":[27],"a":[28,95],"fully":[29,34],"observable":[30,35],"state":[31],"space,":[32],"i.e.":[33],"Markov":[36],"Decision":[37],"Processes":[38],"(MDPs).":[39],"In":[40,80],"real-world":[41],"robotics,":[42],"this":[43,81],"assumption":[44],"unpractical,":[46],"because":[47],"issues":[49],"such":[50],"as":[51],"sensor":[52,56],"sensitivity":[53],"limitations":[54],"and":[55,58,100,111,132],"noise,":[57],"the":[59,65,116,120,127],"lack":[60],"knowledge":[62],"about":[63],"whether":[64],"observation":[66,134],"design":[67],"complete":[69],"or":[70],"not.":[71],"These":[72],"scenarios":[73],"lead":[74],"Partially":[76],"Observable":[77],"MDPs":[78,110],"(POMDPs).":[79],"paper,":[82],"we":[83],"propose":[84],"Long-Short-Term-Memory-based":[85],"Twin":[86],"Delayed":[87],"Deterministic":[89],"Policy":[90],"Gradient":[91],"(LSTM-TD3)":[92],"by":[93],"introducing":[94],"memory":[96,121],"component":[97,122],"TD3,":[99],"compare":[101],"performance":[103],"with":[104],"other":[105],"DRL":[106],"algorithms":[107],"both":[109],"POMDPs.":[112],"Our":[113],"results":[114],"demonstrate":[115],"significant":[117],"advantages":[118],"addressing":[124],"POMDPs,":[125],"including":[126],"ability":[128],"handle":[130],"missing":[131],"noisy":[133],"data.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}