{"id":"https://openalex.org/W4407987950","doi":"https://doi.org/10.1109/cdc56724.2024.10885921","title":"A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations","display_name":"A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407987950","doi":"https://doi.org/10.1109/cdc56724.2024.10885921"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10885921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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/A5004665117","display_name":"Erhan Can Ozcan","orcid":"https://orcid.org/0000-0002-6931-8848"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erhan Can Ozcan","raw_affiliation_strings":["Boston University,Division of Systems Engineering,Boston,MA,USA,02215"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University,Division of Systems Engineering,Boston,MA,USA,02215","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075631895","display_name":"Vittorio Giammarino","orcid":"https://orcid.org/0000-0001-7082-3262"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vittorio Giammarino","raw_affiliation_strings":["Boston University,Division of Systems Engineering,Boston,MA,USA,02215"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University,Division of Systems Engineering,Boston,MA,USA,02215","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026822908","display_name":"James Queeney","orcid":"https://orcid.org/0000-0003-0655-3637"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Queeney","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA,02139"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075696701","display_name":"Ioannis Ch. Paschalidis","orcid":"https://orcid.org/0000-0002-3343-2913"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioannis Ch. Paschalidis","raw_affiliation_strings":["Boston University,Division of Systems Engineering,Department of Electrical and Computer Engineering, Department of Biomedical Engineering,Boston,MA,USA,02215"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University,Division of Systems Engineering,Department of Electrical and Computer Engineering, Department of Biomedical Engineering,Boston,MA,USA,02215","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2933,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9013926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1147","last_page":"1152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.940500020980835,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.940500020980835,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8318020105361938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7880457639694214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5161013007164001},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42251184582710266}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8318020105361938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880457639694214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5161013007164001},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42251184582710266}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10885921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2295827790","https://openalex.org/W2409942531","https://openalex.org/W2581566809","https://openalex.org/W2904246096","https://openalex.org/W2962787969","https://openalex.org/W2963411833","https://openalex.org/W2963802910","https://openalex.org/W2994446013","https://openalex.org/W3127561923","https://openalex.org/W4360584316","https://openalex.org/W4388905406","https://openalex.org/W6637967152","https://openalex.org/W6640174482","https://openalex.org/W6684921986","https://openalex.org/W6696380822","https://openalex.org/W6718092244","https://openalex.org/W6720501231","https://openalex.org/W6730700719","https://openalex.org/W6747387971","https://openalex.org/W6747924173","https://openalex.org/W6748314335","https://openalex.org/W6751526458","https://openalex.org/W6752165109","https://openalex.org/W6753770476","https://openalex.org/W6755724153","https://openalex.org/W6761908843","https://openalex.org/W6763078103","https://openalex.org/W6764053384","https://openalex.org/W6768397756","https://openalex.org/W6768977950","https://openalex.org/W6776026728","https://openalex.org/W6777091672","https://openalex.org/W6779656125","https://openalex.org/W6797052142","https://openalex.org/W6797483895","https://openalex.org/W6802762872","https://openalex.org/W6803550857","https://openalex.org/W6849586761","https://openalex.org/W6849879325","https://openalex.org/W6856470939","https://openalex.org/W6857107556","https://openalex.org/W6870878710"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"how":[3],"to":[4,20],"incorporate":[5],"expert":[6,12,87],"observations":[7],"(without":[8],"explicit":[9],"information":[10],"on":[11,68],"actions)":[13],"into":[14],"a":[15,32,39,45,69],"deep":[16],"reinforcement":[17,35],"learning":[18,36],"setting":[19],"improve":[21],"sample":[22],"efficiency.":[23],"First,":[24],"we":[25,50],"formulate":[26],"an":[27,52],"augmented":[28,64],"policy":[29],"loss":[30,42,65],"combining":[31],"maximum":[33],"entropy":[34],"objective":[37],"with":[38],"behavioral":[40],"cloning":[41],"that":[43,54,76],"leverages":[44],"forward":[46],"dynamics":[47],"model.":[48],"Then,":[49],"propose":[51],"algorithm":[53,79],"automatically":[55],"adjusts":[56],"the":[57,63,77],"weights":[58],"of":[59,71],"each":[60],"component":[61],"in":[62],"function.":[66],"Experiments":[67],"variety":[70],"continuous":[72],"control":[73],"tasks":[74],"demonstrate":[75],"proposed":[78],"outperforms":[80],"various":[81],"benchmarks":[82],"by":[83],"effectively":[84],"utilizing":[85],"available":[86],"observations.":[88]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}