{"id":"https://openalex.org/W4410049270","doi":"https://doi.org/10.1145/3722573.3727827","title":"From Toy to Target: Investigating Representation Transfer for Reinforcement Learning with Implications for Cyber-Physical Systems","display_name":"From Toy to Target: Investigating Representation Transfer for Reinforcement Learning with Implications for Cyber-Physical Systems","publication_year":2025,"publication_date":"2025-05-03","ids":{"openalex":"https://openalex.org/W4410049270","doi":"https://doi.org/10.1145/3722573.3727827"},"language":"en","primary_location":{"id":"doi:10.1145/3722573.3727827","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3722573.3727827","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Workshop on Design Automation for CPS and IoT","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3722573.3727827","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nathan B. Williams","orcid":"https://orcid.org/0009-0008-6959-8852"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nathan B. Williams","raw_affiliation_strings":["Georgia Institute of Technology, Daniel Guggenheim School of Aerospace Engineering, Aerospace Systems Design Laboratory, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0009-0008-6959-8852","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Daniel Guggenheim School of Aerospace Engineering, Aerospace Systems Design Laboratory, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108719440","display_name":"Woong Je Sung","orcid":"https://orcid.org/0000-0003-1915-8556"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Woong Je Sung","raw_affiliation_strings":["Georgia Institute of Technology, Daniel Guggenheim School of Aerospace Engineering, Aerospace Systems Design Laboratory, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0000-0003-1915-8556","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Daniel Guggenheim School of Aerospace Engineering, Aerospace Systems Design Laboratory, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arun Ramamurthy","orcid":"https://orcid.org/0000-0002-5187-4977"},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Ramamurthy","raw_affiliation_strings":["SIEMENS, Princeton, New Jersey, USA"],"raw_orcid":"https://orcid.org/0000-0002-5187-4977","affiliations":[{"raw_affiliation_string":"SIEMENS, Princeton, New Jersey, USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024102827","display_name":"Hyunjee Jin","orcid":"https://orcid.org/0000-0002-7029-5313"},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyunjee Jin","raw_affiliation_strings":["SIEMENS, Princeton, New Jersey, USA"],"raw_orcid":"https://orcid.org/0000-0002-7029-5313","affiliations":[{"raw_affiliation_string":"SIEMENS, Princeton, New Jersey, USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044421630","display_name":"Dimitri N. Mavris","orcid":"https://orcid.org/0000-0001-8783-4988"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitri Mavris","raw_affiliation_strings":["Georgia Institute of Technology, Daniel Guggenheim School of Aerospace Engineering, Aerospace Systems Design Laboratory, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0000-0001-8783-4988","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Daniel Guggenheim School of Aerospace Engineering, Aerospace Systems Design Laboratory, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04036212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9835000038146973,"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"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7675658464431763},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6555330753326416},{"id":"https://openalex.org/keywords/cyber-physical-system","display_name":"Cyber-physical system","score":0.6113126277923584},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5474140048027039},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5392012000083923},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5107722282409668},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4743187129497528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39138346910476685},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3533896207809448},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1724909543991089},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06534364819526672}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7675658464431763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6555330753326416},{"id":"https://openalex.org/C179768478","wikidata":"https://www.wikidata.org/wiki/Q1120057","display_name":"Cyber-physical system","level":2,"score":0.6113126277923584},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5474140048027039},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5392012000083923},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5107722282409668},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4743187129497528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39138346910476685},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3533896207809448},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1724909543991089},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06534364819526672},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3722573.3727827","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3722573.3727827","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Workshop on Design Automation for CPS and IoT","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3722573.3727827","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3722573.3727827","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Workshop on Design Automation for CPS and IoT","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G895292770","display_name":null,"funder_award_id":"GR00012410","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2121517924","https://openalex.org/W3028345072","https://openalex.org/W4214717370","https://openalex.org/W4383112908"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"As":[0],"Cyber-Physical":[1],"Systems":[2],"(CPS)":[3],"become":[4],"more":[5,8,79],"common":[6],"and":[7,25,85,145,176,193],"complex,":[9],"training":[10,84],"reinforcement":[11],"learning":[12,51,178],"(RL)":[13],"agents":[14],"to":[15,48,77,110,155,164,166],"perform":[16],"well":[17],"in":[18,44,52,64,157,187],"these":[19],"large-scale":[20],"environments":[21,47,195],"remains":[22],"both":[23],"challenging":[24],"computationally":[26],"expensive.":[27],"This":[28],"paper":[29],"proposes":[30],"the":[31,127,150,160,191],"Toy":[32,90],"Transfer":[33,91],"Method":[34,92],"(TTM)":[35],"as":[36,99,119],"a":[37,65,78,100,106,116,135,167],"potential":[38],"approach":[39],"for":[40,183],"leveraging":[41],"knowledge":[42,104],"acquired":[43],"small-scale":[45],"toy":[46,67,192],"expedite":[49],"agent":[50,62,87,132,138,152,162],"larger":[53],"environments.":[54],"The":[55,89,123],"key":[56],"idea":[57],"is":[58,93],"that":[59,73,126,173],"an":[60],"RL":[61,185],"trained":[63,139],"well-structured":[66],"environment":[68,98,174],"may":[69,179],"learn":[70],"useful":[71],"representations":[72],"can":[74],"be":[75,180],"transferred":[76],"complex":[80],"target":[81,194],"environment,":[82],"expediting":[83],"improving":[86,184],"efficacy.":[88],"evaluated":[94],"using":[95],"OpenAI's":[96],"Taxi":[97],"case":[101],"study,":[102],"transferring":[103],"from":[105,140],"5x5":[107],"grid":[108,113],"world":[109],"multiple":[111],"7x7":[112],"worlds":[114],"with":[115],"roughly":[117],"twice":[118],"large":[120],"state":[121],"space.":[122],"results":[124,171],"demonstrate":[125],"TTM-enhanced":[128,151],"Deep":[129],"Q-Network":[130],"(DQN)":[131],"consistently":[133],"outperforms":[134],"baseline":[136,161],"DQN":[137],"scratch,":[141],"achieving":[142],"faster":[143],"convergence":[144,156],"higher":[146],"average":[147],"rewards.":[148],"Furthermore,":[149],"often":[153],"leads":[154],"cases":[158],"where":[159],"fails":[163],"converge":[165],"successful":[168],"policy.":[169],"These":[170],"suggest":[172],"abstraction":[175],"transfer":[177],"viable":[181],"strategies":[182],"efficiency":[186],"CPS,":[188],"especially":[189],"when":[190],"are":[196],"structurally":[197],"similar.":[198]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}