{"id":"https://openalex.org/W4290944609","doi":"https://doi.org/10.1145/3534678.3539266","title":"Importance Prioritized Policy Distillation","display_name":"Importance Prioritized Policy Distillation","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290944609","doi":"https://doi.org/10.1145/3534678.3539266"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539266","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5048340011","display_name":"Xinghua Qu","orcid":"https://orcid.org/0000-0001-8072-2019"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xinghua Qu","raw_affiliation_strings":["Bytedance AI Lab, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068243197","display_name":"Yew-Soon Ong","orcid":"https://orcid.org/0000-0002-4480-169X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yew Soon Ong","raw_affiliation_strings":["Nanyang Technological University & A*STAR Centre for Frontier AI, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University & A*STAR Centre for Frontier AI, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041091856","display_name":"Abhishek Gupta","orcid":"https://orcid.org/0000-0002-6080-855X"},"institutions":[{"id":"https://openalex.org/I4210091207","display_name":"Singapore Institute of Manufacturing Technology","ror":"https://ror.org/00f44np30","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210091207","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Abhishek Gupta","raw_affiliation_strings":["Singapore Institute of Manufacturing Technology, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Institute of Manufacturing Technology, Singapore, Singapore","institution_ids":["https://openalex.org/I4210091207"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015951797","display_name":"Pengfei Wei","orcid":"https://orcid.org/0000-0002-1155-6085"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Wei","raw_affiliation_strings":["Bytedance AI Lab, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033957641","display_name":"Zhu Sun","orcid":"https://orcid.org/0000-0002-3350-7022"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhu Sun","raw_affiliation_strings":["Institute of High Performance Computing and Centre for Frontier AI Research & A*STAR, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing and Centre for Frontier AI Research & A*STAR, Singapore, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Bytedance AI Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048340011"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7271,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70943762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1420","last_page":"1429"},"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":0.9886000156402588,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9822999835014343,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8131420612335205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7696104645729065},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6961673498153687},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6478743553161621},{"id":"https://openalex.org/keywords/reciprocal","display_name":"Reciprocal","score":0.5905680060386658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5214540362358093},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.49012383818626404},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48220789432525635},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.456645667552948},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42601048946380615},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3783341646194458},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15296515822410583},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07357609272003174}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8131420612335205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7696104645729065},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6961673498153687},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6478743553161621},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.5905680060386658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5214540362358093},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.49012383818626404},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48220789432525635},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.456645667552948},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42601048946380615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3783341646194458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15296515822410583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07357609272003174},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539266","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1999874108","https://openalex.org/W2032558547","https://openalex.org/W2051228319","https://openalex.org/W2145339207","https://openalex.org/W2149298154","https://openalex.org/W2150468603","https://openalex.org/W2347074400","https://openalex.org/W2560674852","https://openalex.org/W2593390416","https://openalex.org/W2608702473","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2997006708","https://openalex.org/W3034368386","https://openalex.org/W3138154797","https://openalex.org/W3142239405"],"related_works":["https://openalex.org/W2391753177","https://openalex.org/W2996284460","https://openalex.org/W1966306316","https://openalex.org/W2052414331","https://openalex.org/W3003660440","https://openalex.org/W4285058191","https://openalex.org/W2017889482","https://openalex.org/W2735124752","https://openalex.org/W2792667446","https://openalex.org/W2028403663"],"abstract_inverted_index":{"Policy":[0],"distillation":[1],"(PD)":[2],"has":[3],"been":[4],"widely":[5],"studied":[6],"in":[7,24,26,37,100],"deep":[8],"reinforcement":[9],"learning":[10],"(RL),":[11],"while":[12],"existing":[13],"PD":[14,112],"approaches":[15],"assume":[16],"that":[17,74,114,154],"the":[18,58,65,81,84,105,116,127,133,156,161,164],"demonstration":[19],"data":[20],"(i.e.,":[21],"state-action":[22],"pairs":[23],"frames)":[25],"a":[27,43,69,140],"decision":[28],"making":[29],"sequence":[30],"is":[31,42,130],"uniformly":[32],"distributed.":[33],"This":[34],"may":[35],"bring":[36],"unwanted":[38],"bias":[39],"since":[40],"RL":[41,101],"reward":[44,67],"maximizing":[45],"process":[46],"instead":[47],"of":[48,83,135,163],"simple":[49],"label":[50],"matching.":[51],"Given":[52],"such":[53,76],"an":[54,109],"issue,":[55],"we":[56,92,107],"denote":[57],"frame":[59,77,97,128,157],"importance":[60,78,98,110,129,158],"as":[61,122],"its":[62],"contribution":[63],"to":[64,123],"expected":[66],"on":[68,104,118,146],"particular":[70],"frame,":[71],"and":[72,95,149],"hypothesize":[73],"adapting":[75],"could":[79],"benefit":[80],"performance":[82,162],"distilled":[85,165],"student":[86],"policy.":[87],"To":[88],"verify":[89],"our":[90],"hypothesis,":[91],"analyze":[93],"why":[94],"how":[96],"matters":[99],"settings.":[102],"Based":[103],"analysis,":[106],"propose":[108],"prioritized":[111],"framework":[113],"highlights":[115],"training":[117],"important":[119],"frames,":[120],"so":[121],"learn":[124],"efficiently.":[125],"Particularly,":[126],"measured":[131],"by":[132],"reciprocal":[134],"weighted":[136],"Shannon":[137],"entropy":[138],"from":[139],"teacher":[141],"policy's":[142],"action":[143],"prescriptions.":[144],"Experiments":[145],"Atari":[147],"games":[148],"policy":[150],"compression":[151],"tasks":[152],"show":[153],"capturing":[155],"significantly":[159],"boosts":[160],"policies.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}