{"id":"https://openalex.org/W4312711106","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892503","title":"Ensemble Policy Distillation with Reduced Data Distribution Mismatch","display_name":"Ensemble Policy Distillation with Reduced Data Distribution Mismatch","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312711106","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892503"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892503","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":"2161-4407","issn":["2161-4407"],"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 International Joint Conference on Neural Networks (IJCNN)","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/A5039935452","display_name":"Yuxiang Sun","orcid":"https://orcid.org/0000-0002-7704-0559"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxiang Sun","raw_affiliation_strings":["Artificial Intelligence Institute, University of South Carolina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, University of South Carolina","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100360430","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0003-2519-5580"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Artificial Intelligence Institute, University of South Carolina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, University of South Carolina","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I155781252"],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57152519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"110 3","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.988099992275238,"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":0.988099992275238,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9736999869346619,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10036","display_name":"Advanced Neural Network Applications","score":0.9677000045776367,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/distillation","display_name":"Distillation","score":0.8177099823951721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7521891593933105},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6879629492759705},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5964140892028809},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4856189787387848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4643905758857727},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.41235867142677307},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11110442876815796}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.8177099823951721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521891593933105},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6879629492759705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5964140892028809},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4856189787387848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4643905758857727},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.41235867142677307},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11110442876815796},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892503","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":"2161-4407","issn":["2161-4407"],"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 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W114364418","https://openalex.org/W1658008008","https://openalex.org/W1730555343","https://openalex.org/W1821462560","https://openalex.org/W2145339207","https://openalex.org/W2165150801","https://openalex.org/W2174786457","https://openalex.org/W2280163991","https://openalex.org/W2508418541","https://openalex.org/W2596758708","https://openalex.org/W2746553466","https://openalex.org/W2767313115","https://openalex.org/W2904453761","https://openalex.org/W2937282529","https://openalex.org/W2943171176","https://openalex.org/W2947150733","https://openalex.org/W2947433239","https://openalex.org/W2953364219","https://openalex.org/W2963864421","https://openalex.org/W2973567310","https://openalex.org/W2981539019","https://openalex.org/W2981819252","https://openalex.org/W2995509794","https://openalex.org/W2997006708","https://openalex.org/W2997955743","https://openalex.org/W3006670279","https://openalex.org/W3014596384","https://openalex.org/W3022566517","https://openalex.org/W3134774296","https://openalex.org/W4287322058","https://openalex.org/W4298174377","https://openalex.org/W4298858094","https://openalex.org/W4302570325","https://openalex.org/W6684921986","https://openalex.org/W6732837357","https://openalex.org/W6745497480"],"related_works":["https://openalex.org/W4210912933","https://openalex.org/W1562959674","https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W3022038857","https://openalex.org/W4307413493","https://openalex.org/W3139398652","https://openalex.org/W2963350559","https://openalex.org/W2888706357","https://openalex.org/W3105390939"],"abstract_inverted_index":{"Policy":[0,57,135],"distillation":[1,47,66,160],"is":[2,13,33],"a":[3,79,139],"method":[4,141],"for":[5,8,78,104],"model":[6],"compression":[7,38],"deep":[9],"reinforcement":[10],"learning,":[11,128],"which":[12,35],"typically":[14],"applied":[15],"onto":[16],"mobile":[17],"devices":[18],"to":[19,49,74,142],"reduce":[20],"power":[21],"consumption":[22],"and":[23,29,129,157,164],"inference":[24],"time.":[25],"However,":[26],"achieving":[27],"full":[28],"stable":[30],"distilled":[31,98],"policies":[32],"challenging,":[34],"impedes":[36],"higher":[37],"ratios.":[39],"In":[40,84],"this":[41,51],"work,":[42],"we":[43,109],"develop":[44],"two":[45],"policy":[46,82],"algorithms":[48],"address":[50],"problem.":[52],"Our":[53],"first":[54],"algorithm,":[55,133],"Ensemble":[56],"Distillation":[58,136],"(EPD),":[59],"incorporates":[60],"the":[61,85,112,120,131,144,154,158],"idea":[62],"from":[63],"supervised":[64],"learning":[65,156],"that":[67,93,150],"uses":[68],"an":[69],"ensemble":[70,122],"of":[71,114],"teacher":[72,121],"networks":[73,97],"provide":[75],"diverse":[76],"supervision":[77],"compact":[80],"student":[81,96],"network.":[83],"Deep":[86],"Q-Network":[87],"(DQN)":[88],"framework,":[89],"our":[90],"experiments":[91],"verify":[92],"highly":[94],"compressed":[95],"using":[99],"EPD":[100,124],"even":[101],"outperform":[102],"teachers":[103],"numerous":[105],"Atari":[106,162],"games.":[107],"Additionally,":[108],"analyze":[110],"how":[111],"issue":[113],"data":[115],"distribution":[116,145],"mismatch":[117],"caused":[118],"by":[119],"in":[123,161],"negatively":[125],"impacts":[126],"teachers'":[127,155],"introduce":[130],"second":[132],"Double":[134],"(DPD),":[137],"as":[138],"novel":[140],"mitigate":[143],"mismatch.":[146],"Empirical":[147],"results":[148],"show":[149],"DPD":[151],"improves":[152],"both":[153],"student's":[159],"games":[163],"continuous":[165],"control":[166],"tasks.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}