{"id":"https://openalex.org/W4413925439","doi":"https://doi.org/10.1109/icra55743.2025.11128459","title":"SHIRE: Enhancing Sample Efficiency using Human Intuition in REinforcement Learning","display_name":"SHIRE: Enhancing Sample Efficiency using Human Intuition in REinforcement Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925439","doi":"https://doi.org/10.1109/icra55743.2025.11128459"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5101690735","display_name":"Amogh Joshi","orcid":"https://orcid.org/0000-0001-5964-7800"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amogh Joshi","raw_affiliation_strings":["Purdue University,West Lafayette,IN,USA,47907"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008650954","display_name":"Adarsh Kumar Kosta","orcid":"https://orcid.org/0000-0001-6377-6701"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adarsh Kosta","raw_affiliation_strings":["Purdue University,West Lafayette,IN,USA,47907"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031161187","display_name":"Kaushik Roy","orcid":"https://orcid.org/0000-0002-0735-9695"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Roy","raw_affiliation_strings":["Purdue University,West Lafayette,IN,USA,47907"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10769456,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13399","last_page":"13405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8773000240325928,"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":0.8773000240325928,"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/shire","display_name":"Shire","score":0.7964529991149902},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.7709649801254272},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6521122455596924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5604408383369446},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43744444847106934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3635370135307312},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23363038897514343},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13698258996009827},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12343734502792358},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.11356449127197266}],"concepts":[{"id":"https://openalex.org/C2776863037","wikidata":"https://www.wikidata.org/wiki/Q662296","display_name":"Shire","level":2,"score":0.7964529991149902},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.7709649801254272},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6521122455596924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5604408383369446},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43744444847106934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3635370135307312},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23363038897514343},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13698258996009827},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12343734502792358},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.11356449127197266},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1679945064","https://openalex.org/W1981691276","https://openalex.org/W2516809705","https://openalex.org/W2904275768","https://openalex.org/W2907537824","https://openalex.org/W2990747716","https://openalex.org/W2999219213","https://openalex.org/W3000674297","https://openalex.org/W3138915575","https://openalex.org/W3211490618","https://openalex.org/W3212368439","https://openalex.org/W4205982568","https://openalex.org/W4251991763","https://openalex.org/W4312790276","https://openalex.org/W4390874104","https://openalex.org/W4390874575"],"related_works":["https://openalex.org/W2312751881","https://openalex.org/W2318335580","https://openalex.org/W635294811","https://openalex.org/W168377935","https://openalex.org/W2529302696","https://openalex.org/W2027017651","https://openalex.org/W4230522828","https://openalex.org/W626589671","https://openalex.org/W3121606906","https://openalex.org/W85142580"],"abstract_inverted_index":{"The":[0],"ability":[1],"of":[2,73,203],"neural":[3],"networks":[4],"to":[5,29,76,78,94,163],"perform":[6],"robotic":[7],"perception":[8],"and":[9,15,21,24,90,154],"control":[10,26],"tasks":[11,117],"such":[12,85,107,123],"as":[13,47,86,108],"depth":[14],"optical":[16],"flow":[17],"estimation,":[18],"simultaneous":[19],"localization":[20],"mapping":[22],"(SLAM),":[23],"automatic":[25],"has":[27,40],"led":[28],"their":[30,133],"widespread":[31],"adoption":[32],"in":[33,44,105,119,157],"recent":[34],"years.":[35],"Deep":[36,87,159],"Reinforcement":[37],"Learning":[38,89],"(DeepRL)":[39],"been":[41],"used":[42],"extensively":[43],"these":[45],"settings,":[46],"it":[48,68,156],"does":[49],"not":[50,100],"have":[51],"the":[52,102,114,158,175,188,201],"unsustainable":[53],"training":[54,161],"costs":[55],"associated":[56],"with":[57],"supervised":[58],"learning.":[59],"However,":[60],"DeepRL":[61],"suffers":[62],"from":[63],"poor":[64],"sample":[65,134,165,171],"efficiency,":[66],"i.e.,":[67],"requires":[69],"a":[70,142],"large":[71],"number":[72],"environmental":[74],"interactions":[75],"converge":[77],"an":[79],"acceptable":[80],"solution.":[81],"Modern":[82],"RL":[83,127,160,186],"algorithms":[84],"Q":[88],"Soft":[91],"Actor-Critic":[92],"attempt":[93],"remedy":[95],"this":[96,137],"shortcoming":[97],"but":[98],"can":[99,125],"provide":[101],"explainability":[103],"required":[104],"applications":[106],"autonomous":[109],"robotics.":[110,120],"Humans":[111],"intuitively":[112],"understand":[113],"long-time-horizon":[115],"sequential":[116],"common":[118],"Properly":[121],"using":[122,149,155,206],"intuition":[124,148],"make":[126],"policies":[128,204],"more":[129],"explainable":[130],"while":[131],"enhancing":[132],"efficiency.":[135,166],"In":[136],"work,":[138],"we":[139,177],"propose":[140],"SHIRE,":[141],"novel":[143],"framework":[144,168],"for":[145],"encoding":[146],"human":[147],"Probabilistic":[150],"Graphical":[151],"Models":[152],"(PGMs)":[153],"pipeline":[162],"enhance":[164],"Our":[167],"achieves":[169],"25-78%":[170],"efficiency":[172],"gains":[173],"across":[174],"environments":[176],"evaluate":[178],"at":[179],"negligible":[180],"overhead":[181],"cost.":[182],"Additionally,":[183],"by":[184],"teaching":[185],"agents":[187],"encoded":[189],"elementary":[190],"behavior,":[191],"SHIRE":[192],"enhances":[193],"policy":[194],"explainability.":[195],"A":[196],"real-world":[197],"demonstration":[198],"further":[199],"highlights":[200],"efficacy":[202],"trained":[205],"our":[207],"framework.":[208]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}