{"id":"https://openalex.org/W3016244212","doi":"https://doi.org/10.1109/icassp40776.2020.9053393","title":"Learning Diverse Sub-Policies via a Task-Agnostic Regularization on Action Distributions","display_name":"Learning Diverse Sub-Policies via a Task-Agnostic Regularization on Action Distributions","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016244212","doi":"https://doi.org/10.1109/icassp40776.2020.9053393","mag":"3016244212"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5045702955","display_name":"Liangyu Huo","orcid":"https://orcid.org/0000-0002-0703-3978"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangyu Huo","raw_affiliation_strings":["School of Electronic and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103046319","display_name":"Zulin Wang","orcid":"https://orcid.org/0000-0002-1328-7739"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zulin Wang","raw_affiliation_strings":["School of Electronic and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079385534","display_name":"Mai Xu","orcid":"https://orcid.org/0000-0002-0277-3301"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mai Xu","raw_affiliation_strings":["School of Electronic and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004775934","display_name":"Yuhang Song","orcid":"https://orcid.org/0000-0002-7999-0291"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuhang Song","raw_affiliation_strings":["Department of Computer Science, University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9990000128746033,"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":0.9990000128746033,"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/T10260","display_name":"Software Engineering Research","score":0.9438999891281128,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9380000233650208,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7488896250724792},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7437169551849365},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.675945520401001},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6640600562095642},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6116821765899658},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5008759498596191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48119908571243286},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4627317190170288},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4302317500114441},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07801046967506409}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7488896250724792},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7437169551849365},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.675945520401001},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6640600562095642},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6116821765899658},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5008759498596191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48119908571243286},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4627317190170288},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4302317500114441},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07801046967506409},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2033178790","https://openalex.org/W2099471712","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2158548602","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2442341664","https://openalex.org/W2534060593","https://openalex.org/W2592215206","https://openalex.org/W2594829461","https://openalex.org/W2606433045","https://openalex.org/W2736601468","https://openalex.org/W2765602917","https://openalex.org/W2796206912","https://openalex.org/W2803281228","https://openalex.org/W2949267040","https://openalex.org/W2950040888","https://openalex.org/W2963161674","https://openalex.org/W2963262099","https://openalex.org/W2963722050","https://openalex.org/W2963761387","https://openalex.org/W2963830168","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964118262","https://openalex.org/W2964227312","https://openalex.org/W3103780890","https://openalex.org/W4212774754","https://openalex.org/W4294578467","https://openalex.org/W4320013936","https://openalex.org/W6683443546","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6729130418","https://openalex.org/W6734215269","https://openalex.org/W6734325300","https://openalex.org/W6736368053","https://openalex.org/W6741002519","https://openalex.org/W6744935223","https://openalex.org/W6749821205","https://openalex.org/W6765378368","https://openalex.org/W6766234440"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W3183136280","https://openalex.org/W4318559728","https://openalex.org/W2775233965","https://openalex.org/W3114716045","https://openalex.org/W4281847915"],"abstract_inverted_index":{"Automatic":[0],"sub-policy":[1,25],"discovery":[2,45],"has":[3],"recently":[4],"received":[5],"much":[6],"attention":[7],"in":[8],"hierarchical":[9],"reinforcement":[10],"learning":[11,17],"(HRL).":[12],"The":[13],"conventional":[14],"approaches":[15,95],"to":[16,32,63],"sub-policies":[18,48],"suffer":[19],"from":[20],"collapsing":[21],"into":[22],"just":[23],"one":[24],"dominating":[26],"the":[27,34,44,79,82,87,93,106],"whole":[28],"task,":[29],"lacking":[30],"techniques":[31],"ensure":[33],"diversity":[35],"of":[36,46,111],"different":[37,102],"subpolicies.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,54],"formulate":[43],"diverse":[47],"as":[49],"a":[50],"trajectory":[51],"inference.":[52],"Then,":[53],"propose":[55],"an":[56],"information-theoretic":[57],"objective":[58],"based":[59],"on":[60,71,100],"action":[61,75],"distributions":[62],"encourage":[64],"diversity.":[65],"Moreover,":[66],"two":[67,101],"simplifications":[68],"are":[69],"derived":[70],"discrete":[72],"and":[73,109],"continuous":[74],"space":[76],"for":[77],"reducing":[78],"computation.":[80],"Finally,":[81],"experimental":[83],"results":[84],"show":[85],"that":[86],"proposed":[88],"approach":[89],"can":[90],"further":[91],"improve":[92],"state-of-theart":[94],"without":[96],"modifying":[97],"existing":[98],"hyperparameters":[99],"HRL":[103],"domains,":[104],"suggesting":[105],"wide":[107],"applicability":[108],"robustness":[110],"our":[112],"approach.":[113]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}