{"id":"https://openalex.org/W4294690650","doi":"https://doi.org/10.23919/acc53348.2022.9867896","title":"Sample efficient transfer in reinforcement learning for high variable cost environments with an inaccurate source reward model","display_name":"Sample efficient transfer in reinforcement learning for high variable cost environments with an inaccurate source reward model","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4294690650","doi":"https://doi.org/10.23919/acc53348.2022.9867896"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867896","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867896","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"2022 American Control Conference (ACC)","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/A5035835155","display_name":"Md Ferdous Alam","orcid":"https://orcid.org/0000-0002-8469-7591"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Ferdous Alam","raw_affiliation_strings":["The Ohio State University,Department of Mechanical and Aerospace Engineering,Columbus,OH,USA,43210"],"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Mechanical and Aerospace Engineering,Columbus,OH,USA,43210","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032198899","display_name":"Max Shtein","orcid":"https://orcid.org/0000-0003-4844-5108"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max Shtein","raw_affiliation_strings":["University of Michigan,Department of Materials Science and Engineering,Ann Arbor,Michigan,USA,48109"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Materials Science and Engineering,Ann Arbor,Michigan,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084847741","display_name":"Kira Barton","orcid":"https://orcid.org/0000-0003-1047-8078"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kira Barton","raw_affiliation_strings":["University of Michigan,Department of Mechanical Engineering,Ann Arbor,Michigan,USA,48109"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Mechanical Engineering,Ann Arbor,Michigan,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014465771","display_name":"David J. Hoelzle","orcid":"https://orcid.org/0000-0002-3316-5878"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David J. Hoelzle","raw_affiliation_strings":["The Ohio State University,Department of Mechanical and Aerospace Engineering,Columbus,OH,USA,43210"],"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Mechanical and Aerospace Engineering,Columbus,OH,USA,43210","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035835155"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50393234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2892","last_page":"2898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9916999936103821,"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":0.9811000227928162,"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":0.6589779257774353},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6392171382904053},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5982745885848999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5690889954566956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5215351581573486},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5096042156219482},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4992713928222656},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4973008930683136},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4969621002674103},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.45705103874206543},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4130095839500427},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1909484565258026},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14877665042877197},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0842505693435669}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589779257774353},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6392171382904053},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5982745885848999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690889954566956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5215351581573486},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5096042156219482},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4992713928222656},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4973008930683136},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4969621002674103},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.45705103874206543},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4130095839500427},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1909484565258026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14877665042877197},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0842505693435669},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc53348.2022.9867896","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867896","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W158722652","https://openalex.org/W1502922572","https://openalex.org/W1515851193","https://openalex.org/W1585861384","https://openalex.org/W2031727428","https://openalex.org/W2097381042","https://openalex.org/W2109910161","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2152670157","https://openalex.org/W2209913494","https://openalex.org/W2440926996","https://openalex.org/W2606422886","https://openalex.org/W2766447205","https://openalex.org/W2963864421","https://openalex.org/W3159454750","https://openalex.org/W3184586836","https://openalex.org/W6629804754","https://openalex.org/W6634945376","https://openalex.org/W6674600207","https://openalex.org/W6680657880","https://openalex.org/W6684921986","https://openalex.org/W6718190810"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W4310614650","https://openalex.org/W4386738330"],"abstract_inverted_index":{"Here":[0],"we":[1,96,124,144,177],"propose":[2,97],"an":[3,25,75,110],"algorithm":[4],"that":[5,116,179],"combines":[6],"two":[7,134,146],"classic":[8],"ideas,":[9],"transfer":[10],"learning":[11,17,40,49,82,150],"and":[12],"temporal":[13],"abstraction,":[14],"to":[15,38,43,78,183],"accelerate":[16,39],"in":[18,188],"high":[19,34,79,186],"variable":[20],"cost":[21],"environments":[22,55,192],"(HVC-envs).":[23],"In":[24],"HVC-env,":[26],"each":[27],"sampling":[28,80],"of":[29,69,103,157,164,190],"the":[30,45,86,119,162],"environment":[31,88],"incurs":[32],"a":[33,61,66,98,154],"cost,":[35,81],"thus":[36],"methods":[37],"are":[41],"sought":[42],"reduce":[44],"incurred":[46],"cost.":[47],"Transfer":[48],"can":[50,71],"be":[51,72],"useful":[52,105],"for":[53],"such":[54],"by":[56,129,201],"using":[57,153,193],"prior":[58],"knowledge":[59,203],"from":[60,74,109,204],"source":[62,87,120],"environment.":[63],"As":[64],"only":[65],"small":[67,155],"number":[68,156],"samples":[70,159,200],"collected":[73],"HVC-env":[76],"due":[77],"becomes":[83],"challenging":[84],"when":[85],"provides":[89],"inaccurate":[90,111,207],"rewards.":[91],"To":[92],"overcome":[93],"this":[94,126],"challenge":[95],"simple":[99],"but":[100],"effective":[101],"way":[102],"creating":[104],"temporally":[106],"extended":[107],"actions":[108],"physics":[112],"guided":[113],"model":[114],"(PGM)":[115],"acts":[117],"as":[118],"task.":[121],"At":[122],"first":[123],"address":[125],"issue":[127],"theoretically":[128],"providing":[130],"performance":[131],"bounds":[132],"between":[133],"semi-Markov":[135],"Decision":[136],"Processes":[137],"(SMDPs)":[138],"with":[139,206],"different":[140],"reward":[141,208],"functions.":[142],"Later":[143],"develop":[145],"benchmark":[147],"HVC-envs":[148],"where":[149],"must":[151],"happen":[152],"real":[158,199],"(often":[160],"on":[161],"order":[163],"~":[165,194],"10":[166,171,195],"<sup":[167,172,196],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[168,173,197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[169],"or":[170],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>":[174,198],").":[175],"Finally":[176],"show":[178],"it":[180],"is":[181],"possible":[182],"obtain":[184],"sequential":[185],"rewards":[187],"both":[189],"these":[191],"leveraging":[202],"PGMs":[205],"models.":[209]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}