{"id":"https://openalex.org/W4387185477","doi":"https://doi.org/10.3233/faia230288","title":"Enhancing OOD Generalization in Offline Reinforcement Learning with Energy-Based Policy Optimization","display_name":"Enhancing OOD Generalization in Offline Reinforcement Learning with Energy-Based Policy Optimization","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185477","doi":"https://doi.org/10.3233/faia230288"},"language":"en","primary_location":{"id":"doi:10.3233/faia230288","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230288","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230288","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230288","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102714720","display_name":"Hongye Cao","orcid":"https://orcid.org/0000-0002-2537-2295"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongye Cao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764370","display_name":"Shangdong Yang","orcid":"https://orcid.org/0000-0001-5379-9539"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangdong Yang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066091819","display_name":"Jing Huo","orcid":"https://orcid.org/0000-0002-8504-455X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Huo","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025828195","display_name":"Xingguo Chen","orcid":"https://orcid.org/0000-0002-0221-733X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingguo Chen","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066091819"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.5054,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68117222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965000152587891,"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":0.9965000152587891,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9539999961853027,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.944100022315979,"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/generalization","display_name":"Generalization","score":0.833050012588501},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7560484409332275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7346798181533813},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.6544607281684875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5838770866394043},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4871070384979248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4827089309692383},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.133466899394989}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.833050012588501},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7560484409332275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346798181533813},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.6544607281684875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5838770866394043},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4871070384979248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4827089309692383},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.133466899394989},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230288","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230288","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230288","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230288","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230288","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230288","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2328581383","display_name":null,"funder_award_id":"62276128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2767813700","display_name":null,"funder_award_id":"62192783","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G669068149","display_name":null,"funder_award_id":"62276142","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7334411499","display_name":null,"funder_award_id":"62206133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G840559539","display_name":null,"funder_award_id":"KFKT2022B12","funder_id":"https://openalex.org/F4320326895","funder_display_name":"State Key Laboratory of Novel Software Technology"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326895","display_name":"State Key Laboratory of Novel Software Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185477.pdf","grobid_xml":"https://content.openalex.org/works/W4387185477.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2161914416","https://openalex.org/W2436711315","https://openalex.org/W2739473244","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2904453761","https://openalex.org/W2923762280","https://openalex.org/W2936496719","https://openalex.org/W2962787969","https://openalex.org/W2990984513","https://openalex.org/W3016525976","https://openalex.org/W3016705845","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3034084488","https://openalex.org/W3089760622","https://openalex.org/W3092527263","https://openalex.org/W3123348991","https://openalex.org/W3130091361","https://openalex.org/W3130177876","https://openalex.org/W3134294674","https://openalex.org/W3136208045","https://openalex.org/W3153007185","https://openalex.org/W3166131857","https://openalex.org/W3166795773","https://openalex.org/W3168236455","https://openalex.org/W3172360140","https://openalex.org/W3183035190","https://openalex.org/W3185083385","https://openalex.org/W3201700917","https://openalex.org/W3202125656","https://openalex.org/W3203299027","https://openalex.org/W3203827806","https://openalex.org/W3206246732","https://openalex.org/W3208245767","https://openalex.org/W4221143805","https://openalex.org/W4225110331","https://openalex.org/W4226345898","https://openalex.org/W4287750003","https://openalex.org/W4294791786","https://openalex.org/W4297792190","https://openalex.org/W4297915158","https://openalex.org/W4298876402"],"related_works":["https://openalex.org/W1968270095","https://openalex.org/W2220129715","https://openalex.org/W4296478327","https://openalex.org/W2042397106","https://openalex.org/W4361730764","https://openalex.org/W1965029248","https://openalex.org/W2333625343","https://openalex.org/W1960072520","https://openalex.org/W2023776155","https://openalex.org/W2381411913"],"abstract_inverted_index":{"Offline":[0,21],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"is":[4,23,111,165],"an":[5,92],"important":[6],"research":[7],"domain":[8],"for":[9,98,113],"real-world":[10],"applications":[11],"because":[12],"it":[13],"can":[14,141,172],"avert":[15],"expensive":[16],"and":[17,36,69,145,153,189],"dangerous":[18],"online":[19],"exploration.":[20],"RL":[22,44],"prone":[24],"to":[25,49,52,126,167],"extrapolation":[26,54,88],"errors":[27],"caused":[28],"by":[29,39],"the":[30,47,60,78,81,106,114,128,143,149,155,179,186],"distribution":[31,107],"shift":[32],"between":[33],"offline":[34,43,50,109],"datasets":[35,181],"states":[37],"visited":[38],"behavior":[40,51,135],"policy.":[41,129],"Existing":[42],"methods":[45,58,188],"constrain":[46,127],"policy":[48,82],"prevent":[53],"errors.":[55],"But":[56],"these":[57],"limit":[59],"generalization":[61,74,79,118,152],"potential":[62],"of":[63,80,108,116,121,132,138,151,157],"agents":[64],"in":[65,83,136,160],"Out-Of-Distribution":[66],"(OOD)":[67],"regions":[68,85],"cannot":[70],"effectively":[71],"evaluate":[72],"OOD":[73,84,99,117,198],"behavior.":[75],"To":[76,147],"improve":[77,148,173],"while":[86],"avoiding":[87],"errors,":[89],"we":[90],"propose":[91],"Energy-Based":[93],"Policy":[94],"Optimization":[95],"(EBPO)":[96],"method":[97],"generalization.":[100,199],"An":[101],"energy":[102,139],"function":[103],"based":[104],"on":[105,123,178,193],"data":[110],"proposed":[112],"evaluation":[115],"behavior,":[119],"instead":[120],"relying":[122],"model":[124],"discrepancies":[125],"The":[130],"way":[131],"quantifying":[133],"exploration":[134],"terms":[137],"values":[140],"balance":[142],"return":[144],"risk.":[146],"stability":[150],"solve":[154],"problem":[156],"sparse":[158],"reward":[159],"complex":[161],"environment,":[162],"episodic":[163],"memory":[164],"applied":[166],"store":[168],"successful":[169],"experiences":[170],"that":[171,183,196],"sample":[174],"efficiency.":[175],"Extensive":[176],"experiments":[177],"D4RL":[180],"demonstrate":[182],"EBPO":[184],"outperforms":[185],"state-of-the-art":[187],"achieves":[190],"robust":[191],"performance":[192],"challenging":[194],"tasks":[195],"require":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}