{"id":"https://openalex.org/W4390188349","doi":"https://doi.org/10.1109/icdl55364.2023.10364540","title":"Learning, Fast and Slow: A Goal-Directed Memory-Based Approach for Dynamic Environments","display_name":"Learning, Fast and Slow: A Goal-Directed Memory-Based Approach for Dynamic Environments","publication_year":2023,"publication_date":"2023-11-09","ids":{"openalex":"https://openalex.org/W4390188349","doi":"https://doi.org/10.1109/icdl55364.2023.10364540"},"language":"en","primary_location":{"id":"doi:10.1109/icdl55364.2023.10364540","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icdl55364.2023.10364540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Development and Learning (ICDL)","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/A5053162426","display_name":"John Chong Min Tan","orcid":"https://orcid.org/0009-0005-9463-8770"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"John Chong Min Tan","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069355437","display_name":"Mehul Motani","orcid":"https://orcid.org/0000-0003-3262-0207"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mehul Motani","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering","Institute of Data Science, N.1 Institute for Health, Institute for Digital Medicine, National University of Singapore","Department of Electrical and Computer Engineering, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Institute of Data Science, N.1 Institute for Health, Institute for Digital Medicine, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17816039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9851999878883362,"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":0.8577464818954468},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8239511251449585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5758414268493652},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5264611840248108},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4922987222671509},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4409746527671814},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.4140707552433014},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4129638075828552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8577464818954468},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8239511251449585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5758414268493652},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5264611840248108},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4922987222671509},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4409746527671814},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.4140707552433014},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4129638075828552},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl55364.2023.10364540","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icdl55364.2023.10364540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1547304459","https://openalex.org/W1771410628","https://openalex.org/W1933687796","https://openalex.org/W2041692808","https://openalex.org/W2126316555","https://openalex.org/W2141998004","https://openalex.org/W2257979135","https://openalex.org/W2736601468","https://openalex.org/W2898268489","https://openalex.org/W2963523627","https://openalex.org/W2964043796","https://openalex.org/W3018036994","https://openalex.org/W3129322645","https://openalex.org/W3197608410","https://openalex.org/W3216772467","https://openalex.org/W4214717370","https://openalex.org/W4282938007","https://openalex.org/W4298857966","https://openalex.org/W4385245566","https://openalex.org/W6616173779","https://openalex.org/W6638018090","https://openalex.org/W6692846177","https://openalex.org/W6739901393","https://openalex.org/W6784049536","https://openalex.org/W6804601995","https://openalex.org/W6838845867"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2037601570","https://openalex.org/W2912947802","https://openalex.org/W2123856982"],"abstract_inverted_index":{"Model-based":[0],"next":[1,64],"state":[2,5,46,69,73,97],"prediction":[3,7],"and":[4,70,95,139,158,163,168,189,194],"value":[6],"are":[8,161],"slow":[9,40,159],"to":[10,61,186],"converge.":[11],"To":[12],"address":[13],"these":[14],"challenges,":[15],"we":[16,26,37,48,75],"do":[17,27],"the":[18,39,50,63,67,71,77,100,166,178],"following:":[19],"i)":[20],"Instead":[21,43],"of":[22,44,170,180],"a":[23,31,58,114,122,199],"neural":[24,59],"network,":[25],"model-based":[28],"planning":[29],"using":[30,53,57,86],"parallel":[32],"memory":[33,171],"retrieval":[34,172],"system":[35],"(which":[36,74],"term":[38,76],"mechanism);":[41],"ii)":[42],"learning":[45],"values,":[47],"guide":[49],"agent's":[51],"actions":[52],"goal-directed":[54,81,200],"exploration,":[55],"by":[56],"network":[60],"choose":[62],"action":[65,90],"given":[66,92],"current":[68],"goal":[72,96],"fast":[78,157],"mechanism).":[79],"The":[80],"exploration":[82],"is":[83],"trained":[84],"online":[85],"self-supervised":[87],"learning,":[88],"via":[89],"selection":[91],"any":[93],"start":[94],"experienced":[98],"in":[99,121,198],"trajectory":[101],"obtained":[102],"during":[103],"hippocampal":[104],"replay.":[105],"Empirical":[106],"studies":[107,153],"show":[108],"that":[109,155,177],"our":[110],"proposed":[111],"method":[112],"has":[113],"91.9%":[115],"solve":[116],"rate":[117],"across":[118],"100":[119],"episodes":[120],"dynamically":[123],"changing":[124],"grid":[125],"world,":[126],"significantly":[127],"outperforming":[128],"state-of-the-art":[129],"actor":[130],"critic":[131],"mechanisms":[132,160],"such":[133,148],"as":[134,142,144,149],"PPO":[135],"(61.2%),":[136],"TRPO":[137],"(26.1%)":[138],"A2C":[140],"(23.9%),":[141],"well":[143],"replay":[145],"buffer":[146],"methods":[147],"DQN":[150],"(4.9%).":[151],"Ablation":[152],"demonstrate":[154],"both":[156,165],"crucial,":[162],"increasing":[164],"depth":[167],"breadth":[169],"improves":[173],"performance.":[174],"We":[175],"posit":[176],"future":[179],"Reinforcement":[181],"Learning":[182],"(RL)":[183],"will":[184],"be":[185],"model":[187],"goals":[188],"sub-goals":[190],"for":[191],"various":[192],"tasks,":[193],"plan":[195],"it":[196],"out":[197],"memory-based":[201],"approach.":[202]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}