{"id":"https://openalex.org/W4383108607","doi":"https://doi.org/10.1109/icra48891.2023.10161154","title":"Using Memory-Based Learning to Solve Tasks with State-Action Constraints","display_name":"Using Memory-Based Learning to Solve Tasks with State-Action Constraints","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108607","doi":"https://doi.org/10.1109/icra48891.2023.10161154"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161154","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10161154","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 Robotics and Automation (ICRA)","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/A5031824098","display_name":"Mrinal Verghese","orcid":"https://orcid.org/0000-0002-6407-2957"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mrinal Verghese","raw_affiliation_strings":["Robotics Institute at Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055330939","display_name":"Christopher G. Atkeson","orcid":"https://orcid.org/0000-0003-4265-8452"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Atkeson","raw_affiliation_strings":["Robotics Institute at Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031824098"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53685003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"90","issue":null,"first_page":"9558","last_page":"9565"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.995199978351593,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.989300012588501,"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/computer-science","display_name":"Computer science","score":0.8400835394859314},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7916274666786194},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7165088653564453},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6329038739204407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6100565195083618},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5733240842819214},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.548564612865448},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5306020379066467},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.46758556365966797},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4433175027370453},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3793027400970459},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11390259861946106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8400835394859314},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7916274666786194},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7165088653564453},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6329038739204407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6100565195083618},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5733240842819214},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.548564612865448},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5306020379066467},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.46758556365966797},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4433175027370453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3793027400970459},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11390259861946106},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161154","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10161154","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 Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3123056024","display_name":null,"funder_award_id":"IIS-1849287","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1509999309","https://openalex.org/W1518336263","https://openalex.org/W1597173708","https://openalex.org/W1832110895","https://openalex.org/W1975142260","https://openalex.org/W1994349244","https://openalex.org/W2037958061","https://openalex.org/W2060119621","https://openalex.org/W2107590913","https://openalex.org/W2145339207","https://openalex.org/W2222874733","https://openalex.org/W2259002239","https://openalex.org/W2293698677","https://openalex.org/W2337392266","https://openalex.org/W2418783521","https://openalex.org/W2531894595","https://openalex.org/W2736337778","https://openalex.org/W2787066086","https://openalex.org/W2805516822","https://openalex.org/W2914261249","https://openalex.org/W2939969410","https://openalex.org/W2963437685","https://openalex.org/W2968556640","https://openalex.org/W2972340186","https://openalex.org/W3004133887","https://openalex.org/W3004348851","https://openalex.org/W3089355520","https://openalex.org/W3097484130","https://openalex.org/W3132058511","https://openalex.org/W3149166261","https://openalex.org/W3169676024","https://openalex.org/W3207647944","https://openalex.org/W3209765550","https://openalex.org/W4210969899","https://openalex.org/W4226016878","https://openalex.org/W4250881727","https://openalex.org/W4281630793","https://openalex.org/W4282938007","https://openalex.org/W4287209565","https://openalex.org/W4287558444","https://openalex.org/W4297744798","https://openalex.org/W4297752578","https://openalex.org/W6630573394","https://openalex.org/W6748115133","https://openalex.org/W6753537504","https://openalex.org/W6761347996"],"related_works":["https://openalex.org/W1564680838","https://openalex.org/W2003125260","https://openalex.org/W2060591604","https://openalex.org/W1992291644","https://openalex.org/W2166791242","https://openalex.org/W2585162246","https://openalex.org/W1934413089","https://openalex.org/W2098419343","https://openalex.org/W2051178964","https://openalex.org/W2989714914"],"abstract_inverted_index":{"Tasks":[0],"where":[1],"the":[2,10,32,36,100,122],"set":[3],"of":[4,44,103,108,124,152],"possible":[5],"actions":[6,109],"depend":[7],"discontinuously":[8],"on":[9,127],"state":[11],"pose":[12],"a":[13,23,94],"significant":[14],"challenge":[15],"for":[16],"current":[17],"reinforcement":[18,161],"learning":[19,96,126,162],"algorithms.":[20],"For":[21],"example,":[22],"locked":[24],"door":[25,37],"must":[26],"be":[27,39,70],"first":[28],"unlocked,":[29],"and":[30,52,80,105,116,130,139,141,158],"then":[31],"handle":[33],"turned":[34],"before":[35],"can":[38,69],"opened.":[40],"The":[41],"sequential":[42],"nature":[43,102],"these":[45,90,111,148],"tasks":[46,112,132,149],"makes":[47],"obtaining":[48],"final":[49],"rewards":[50],"difficult,":[51],"transferring":[53],"information":[54],"between":[55,137],"task":[56],"variants":[57],"using":[58],"continuous":[59],"learned":[60],"values":[61],"such":[62],"as":[63],"weights":[64],"rather":[65],"than":[66,155],"discrete":[67],"symbols":[68],"inefficient.":[71],"Our":[72],"key":[73],"insight":[74],"is":[75],"that":[76,78,98],"agents":[77],"act":[79],"think":[81],"symbolically":[82],"are":[83],"often":[84],"more":[85],"effective":[86],"in":[87,110],"dealing":[88],"with":[89,133],"tasks.":[91],"We":[92,120],"propose":[93],"memory-based":[95,125],"approach":[97],"leverages":[99],"symbolic":[101],"constraints":[104,136],"temporal":[106],"ordering":[107],"to":[113,146],"quickly":[114],"acquire":[115],"transfer":[117],"high-level":[118],"information.":[119],"evaluate":[121],"performance":[123],"both":[128,156],"real":[129],"simulated":[131],"approximately":[134],"discontinuous":[135],"states":[138],"actions,":[140],"show":[142],"our":[143],"method":[144],"learns":[145],"solve":[147],"an":[150],"order":[151],"magnitude":[153],"faster":[154],"model-based":[157],"model-free":[159],"deep":[160],"methods.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}