{"id":"https://openalex.org/W4394674207","doi":"https://doi.org/10.1109/lra.2024.3387134","title":"Adaptive Curriculum Learning With Successor Features for Imbalanced Compositional Reward Functions","display_name":"Adaptive Curriculum Learning With Successor Features for Imbalanced Compositional Reward Functions","publication_year":2024,"publication_date":"2024-04-10","ids":{"openalex":"https://openalex.org/W4394674207","doi":"https://doi.org/10.1109/lra.2024.3387134"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3387134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3387134","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5086854188","display_name":"L\u00e1szl\u00f3 Sz\u0151ke","orcid":"https://orcid.org/0000-0001-9926-4054"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Laszlo Szoke","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary","Robert Bosch Kf, Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Robert Bosch Kf, Hungary","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073638946","display_name":"Shahaf Shperberg","orcid":"https://orcid.org/0000-0001-7683-3031"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shahaf S. Shperberg","raw_affiliation_strings":["Ben-Gurion University, Beer Sheva, Israel"],"affiliations":[{"raw_affiliation_string":"Ben-Gurion University, Beer Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073269118","display_name":"Jarrett Holtz","orcid":"https://orcid.org/0000-0001-7917-9864"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jarrett Holtz","raw_affiliation_strings":["Robert Bosch LLC., Budapest, Hungary","University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Robert Bosch LLC., Budapest, Hungary","institution_ids":[]},{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059194708","display_name":"Alessandro Allievi","orcid":"https://orcid.org/0000-0001-5793-7679"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alessandro Allievi","raw_affiliation_strings":["Robert Bosch LLC., Budapest, Hungary","University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Robert Bosch LLC., Budapest, Hungary","institution_ids":[]},{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086854188"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":1.0911,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79612751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"9","issue":"6","first_page":"5174","last_page":"5181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9735000133514404,"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":0.9735000133514404,"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/T14082","display_name":"Modeling, Simulation, and Optimization","score":0.9244999885559082,"subfield":{"id":"https://openalex.org/subfields/2607","display_name":"Discrete Mathematics and Combinatorics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/successor-cardinal","display_name":"Successor cardinal","score":0.9447124004364014},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.48705247044563293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4447741210460663},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4212890863418579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4102063477039337},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35169780254364014},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16813009977340698},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.1067553162574768}],"concepts":[{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.9447124004364014},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.48705247044563293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4447741210460663},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4212890863418579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4102063477039337},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35169780254364014},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16813009977340698},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.1067553162574768},{"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:10.1109/lra.2024.3387134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3387134","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2056354534","https://openalex.org/W2138965998","https://openalex.org/W2152166054","https://openalex.org/W2201581102","https://openalex.org/W2296073425","https://openalex.org/W2624731731","https://openalex.org/W2736601468","https://openalex.org/W2742143911","https://openalex.org/W2795921402","https://openalex.org/W2903634288","https://openalex.org/W2903709398","https://openalex.org/W2962244319","https://openalex.org/W2991489433","https://openalex.org/W2994847258","https://openalex.org/W2994987910","https://openalex.org/W2994995984","https://openalex.org/W3072315125","https://openalex.org/W3123742938","https://openalex.org/W3135037631","https://openalex.org/W3168682563","https://openalex.org/W4213443150","https://openalex.org/W4285600796","https://openalex.org/W4286890519","https://openalex.org/W4297781990","https://openalex.org/W4298857966","https://openalex.org/W4376988891","https://openalex.org/W6637967152","https://openalex.org/W6680080562","https://openalex.org/W6687681856","https://openalex.org/W6718190810","https://openalex.org/W6737893269","https://openalex.org/W6737937804","https://openalex.org/W6741002519","https://openalex.org/W6742069676","https://openalex.org/W6743333067","https://openalex.org/W6743660412","https://openalex.org/W6747473740","https://openalex.org/W6752963931","https://openalex.org/W6764281707","https://openalex.org/W6770704954","https://openalex.org/W6771828045","https://openalex.org/W6784364114","https://openalex.org/W6791374197","https://openalex.org/W6796083036","https://openalex.org/W6796188362","https://openalex.org/W6796505199","https://openalex.org/W6811261647","https://openalex.org/W6840804450","https://openalex.org/W6853523444"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"This":[0,85],"work":[1],"addresses":[2],"the":[3,44,66,81],"challenge":[4],"of":[5,18,69],"reinforcement":[6],"learning":[7,23,77,90],"with":[8],"reward":[9,31,46,71,100],"functions":[10,32],"that":[11,41,95],"feature":[12],"highly":[13],"imbalanced":[14,30,70],"components":[15],"in":[16],"terms":[17],"importance":[19],"and":[20,107],"scale.":[21],"Reinforcement":[22],"algorithms":[24],"generally":[25],"struggle":[26],"to":[27,38,58,92],"handle":[28],"such":[29],"effectively.":[33],"Consequently,":[34],"they":[35],"often":[36],"converge":[37],"suboptimal":[39],"policies":[40,94],"favor":[42],"only":[43],"dominant":[45],"component.":[47],"For":[48],"example,":[49],"agents":[50],"might":[51],"adopt":[52],"passive":[53],"strategies,":[54],"avoiding":[55],"any":[56],"action":[57],"evade":[59],"potentially":[60],"unsafe":[61],"outcomes":[62],"entirely.":[63],"To":[64],"mitigate":[65],"adverse":[67],"effects":[68],"functions,":[72],"we":[73],"introduce":[74],"a":[75,104],"curriculum":[76],"approach":[78,87],"based":[79],"on":[80],"successor":[82],"features":[83],"representation.":[84],"novel":[86],"enables":[88],"our":[89],"system":[91],"acquire":[93],"take":[96],"into":[97],"account":[98],"all":[99],"components,":[101],"allowing":[102],"for":[103],"more":[105],"balanced":[106],"versatile":[108],"decision-making":[109],"process.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}