{"id":"https://openalex.org/W4310280900","doi":"https://doi.org/10.48550/arxiv.2211.13743","title":"SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration","display_name":"SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4310280900","doi":"https://doi.org/10.48550/arxiv.2211.13743"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.13743","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.13743","pdf_url":"https://arxiv.org/pdf/2211.13743","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.13743","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001501751","display_name":"Giulia Vezzani","orcid":"https://orcid.org/0000-0002-4151-6447"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vezzani, Giulia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005912318","display_name":"Dhruva Tirumala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tirumala, Dhruva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002747297","display_name":"Markus Wulfmeier","orcid":"https://orcid.org/0000-0003-1802-4492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wulfmeier, Markus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008638246","display_name":"Dushyant Rao","orcid":"https://orcid.org/0000-0002-1372-2884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rao, Dushyant","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007133617","display_name":"Abbas Abdolmaleki","orcid":"https://orcid.org/0000-0001-6692-5856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdolmaleki, Abbas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058953211","display_name":"Benjamin M. Moran","orcid":"https://orcid.org/0000-0001-5230-0863"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moran, Ben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030073861","display_name":"Tuomas Haarnoja","orcid":"https://orcid.org/0009-0007-2973-9246"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haarnoja, Tuomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102771619","display_name":"Jan Humplik","orcid":"https://orcid.org/0000-0002-7573-7635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Humplik, Jan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018196238","display_name":"Roland Hafner","orcid":"https://orcid.org/0000-0001-8061-8828"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hafner, Roland","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053312475","display_name":"Michael Neunert","orcid":"https://orcid.org/0000-0003-2080-8376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neunert, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063252645","display_name":"Claudio Fantacci","orcid":"https://orcid.org/0000-0002-9980-3617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fantacci, Claudio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026388725","display_name":"Tim Hertweck","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hertweck, Tim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054636066","display_name":"Thomas Lampe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lampe, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006431582","display_name":"Fereshteh Sadeghi","orcid":"https://orcid.org/0000-0003-4058-5261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sadeghi, Fereshteh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062951341","display_name":"Nicolas Heess","orcid":"https://orcid.org/0000-0001-7876-9256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heess, Nicolas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Riedmiller, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9958000183105469,"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":0.9958000183105469,"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":0.9247000217437744,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9115999937057495,"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/computer-science","display_name":"Computer science","score":0.7981246709823608},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.7711397409439087},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.681663453578949},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5959565043449402},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5925325751304626},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5586035251617432},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5378016829490662},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.522476077079773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4722703695297241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45837923884391785},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.0842340886592865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981246709823608},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7711397409439087},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.681663453578949},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5959565043449402},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5925325751304626},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5586035251617432},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5378016829490662},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.522476077079773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4722703695297241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45837923884391785},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0842340886592865},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.13743","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.13743","pdf_url":"https://arxiv.org/pdf/2211.13743","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.13743","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.13743","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.13743","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.13743","pdf_url":"https://arxiv.org/pdf/2211.13743","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2083794993","https://openalex.org/W352609212","https://openalex.org/W1511772879","https://openalex.org/W4379115841","https://openalex.org/W4200340037","https://openalex.org/W608917066","https://openalex.org/W4283652261","https://openalex.org/W585424826","https://openalex.org/W564602992"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,61,98,105,158],"effectively":[3],"reuse":[4,21],"prior":[5],"knowledge":[6],"is":[7,22],"a":[8,52,145,153],"key":[9],"requirement":[10],"when":[11,64],"building":[12],"general":[13],"and":[14,83,93,128,150],"flexible":[15],"Reinforcement":[16],"Learning":[17],"(RL)":[18],"agents.":[19],"Skill":[20],"one":[23],"of":[24,56,147,156,162,165],"the":[25,43,114,119,136,160],"most":[26],"common":[27,71],"approaches,":[28],"but":[29,112,133],"current":[30],"methods":[31,90,143],"have":[32],"considerable":[33],"limitations.For":[34],"example,":[35],"fine-tuning":[36],"an":[37,95],"existing":[38,89,107],"policy":[39,44,116],"frequently":[40],"fails,":[41],"as":[42],"can":[45,59,91],"degrade":[46],"rapidly":[47],"early":[48],"in":[49,81],"training.":[50],"In":[51],"similar":[53],"vein,":[54],"distillation":[55],"expert":[57],"behavior":[58],"lead":[60],"poor":[62],"results":[63],"given":[65],"sub-optimal":[66],"experts.":[67],"We":[68,86],"compare":[69],"several":[70],"approaches":[72],"for":[73,110],"skill":[74],"transfer":[75],"on":[76],"multiple":[77],"domains":[78],"including":[79],"changes":[80],"task":[82],"system":[84],"dynamics.":[85],"identify":[87],"how":[88],"fail":[92],"introduce":[94],"alternative":[96],"approach":[97,103],"mitigate":[99],"these":[100],"problems.":[101],"Our":[102],"learns":[104,113],"sequence":[106],"temporally-extended":[108],"skills":[109],"exploration":[111],"final":[115,137],"directly":[117],"from":[118],"raw":[120],"experience.":[121],"This":[122],"conceptual":[123],"split":[124],"enables":[125],"rapid":[126],"adaptation":[127],"thus":[129],"efficient":[130],"data":[131],"collection":[132],"without":[134],"constraining":[135],"solution.It":[138],"significantly":[139],"outperforms":[140],"many":[141],"classical":[142],"across":[144],"suite":[146],"evaluation":[148],"tasks":[149],"we":[151],"use":[152],"broad":[154],"set":[155],"ablations":[157],"highlight":[159],"importance":[161],"differentc":[163],"omponents":[164],"our":[166],"method.":[167]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}