{"id":"https://openalex.org/W7063730537","doi":null,"title":"Adaptively combining skill embeddings for Reinforcement Learning agents","display_name":"Adaptively combining skill embeddings for Reinforcement Learning agents","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W7063730537"},"language":"en","primary_location":{"id":"pmh:oai:etd.adm.unipi.it:etd-06042024-161839","doi":null,"is_oa":true,"landing_page_url":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/","pdf_url":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/unrestricted/_Master_Thesis__Skilled_RL_Agents.pdf","source":{"id":"https://openalex.org/S4306401800","display_name":"Electronic Theses and Dissertations Repository (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/","raw_type":"text"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/unrestricted/_Master_Thesis__Skilled_RL_Agents.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092347048","display_name":"Giacomo Carf\u00ec","orcid":"https://orcid.org/0009-0002-7840-8957","observed_orcids":["https://orcid.org/0009-0002-7840-8957"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"CARFI', GIACOMO","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5092347048"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/foundation-models","display_name":"foundation models","score":0.5910000205039978},{"id":"https://openalex.org/keywords/state-representation","display_name":"state representation","score":0.7519999742507935},{"id":"https://openalex.org/keywords/atari-games","display_name":"Atari games","score":0.6579999923706055},{"id":"https://openalex.org/keywords/out-of-distribution-data","display_name":"out-of-distribution data","score":0.902999997138977},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"lifelong learning","score":0.859000027179718},{"id":"https://openalex.org/keywords/reinforcement-learning-agents","display_name":"reinforcement learning agents","score":0.671999990940094}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8224999904632568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6815000176429749},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5202000141143799},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:etd.adm.unipi.it:etd-06042024-161839","doi":null,"is_oa":true,"landing_page_url":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/","pdf_url":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/unrestricted/_Master_Thesis__Skilled_RL_Agents.pdf","source":{"id":"https://openalex.org/S4306401800","display_name":"Electronic Theses and Dissertations Repository (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:etd.adm.unipi.it:etd-06042024-161839","doi":null,"is_oa":true,"landing_page_url":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/","pdf_url":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/unrestricted/_Master_Thesis__Skilled_RL_Agents.pdf","source":{"id":"https://openalex.org/S4306401800","display_name":"Electronic Theses and Dissertations Repository (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://etd.adm.unipi.it/theses/available/etd-06042024-161839/","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7063730537.pdf","grobid_xml":"https://content.openalex.org/works/W7063730537.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1504008138","https://openalex.org/W1757796397","https://openalex.org/W2100677568","https://openalex.org/W2112796928","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2160815625","https://openalex.org/W2173248099","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2293467699","https://openalex.org/W2581082771","https://openalex.org/W2581624817","https://openalex.org/W2608997467","https://openalex.org/W2736601468","https://openalex.org/W2775536965","https://openalex.org/W2788388592","https://openalex.org/W2896457183","https://openalex.org/W2919115771","https://openalex.org/W2964110616","https://openalex.org/W2981030070","https://openalex.org/W2982316857","https://openalex.org/W2992977009","https://openalex.org/W2996037775","https://openalex.org/W2997423597","https://openalex.org/W3035524453","https://openalex.org/W3113356146","https://openalex.org/W3157410348","https://openalex.org/W3175752186","https://openalex.org/W3206188474","https://openalex.org/W4220904111","https://openalex.org/W4226167593","https://openalex.org/W4239510810","https://openalex.org/W4296123194","https://openalex.org/W4312910992","https://openalex.org/W4312933868","https://openalex.org/W4378505261","https://openalex.org/W4380993732","https://openalex.org/W4381586832","https://openalex.org/W4381714048","https://openalex.org/W4385473486","https://openalex.org/W4385968027","https://openalex.org/W4391832620","https://openalex.org/W4394946817","https://openalex.org/W4399151176","https://openalex.org/W4404838758","https://openalex.org/W6960139023"],"related_works":["https://openalex.org/W4416105962","https://openalex.org/W3110876951","https://openalex.org/W7133913960","https://openalex.org/W1524054883","https://openalex.org/W86588979","https://openalex.org/W6927250570","https://openalex.org/W3092318615","https://openalex.org/W2889732123","https://openalex.org/W2989957090","https://openalex.org/W6950639296"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"aims":[3],"to":[4,29,55,66,70,121,148,150],"learn":[5,23],"agent":[6],"behavioural":[7],"policies":[8],"by":[9,15,53],"maximizing":[10],"the":[11,18,34,38,47,57,114],"cumulative":[12],"reward":[13],"obtained":[14],"interacting":[16],"with":[17,135],"environment.":[19],"Standard":[20],"RL":[21],"approaches":[22],"an":[24,72],"end-to-end":[25],"mapping":[26],"from":[27],"observations":[28],"action":[30],"spaces":[31],"which":[32,49,86],"define":[33],"agent's":[35],"behavior.":[36],"On":[37],"other":[39],"hand,":[40],"Foundational":[41,91],"Models":[42],"learns":[43],"different":[44,90,108,151],"representations":[45,69],"of":[46,89,116,129],"world":[48],"can":[50],"be":[51],"used":[52],"agents":[54,147],"accelerate":[56],"learning":[58,146],"process.":[59],"In":[60],"this":[61],"thesis,":[62],"we":[63,77,94,112],"study":[64],"how":[65,120],"combine":[67],"these":[68],"create":[71],"enhanced":[73],"state":[74],"representation.":[75],"Specifically,":[76],"propose":[78],"a":[79],"technique":[80],"called":[81],"Weight":[82],"Sharing":[83],"Attention":[84],"(WSA)":[85],"combines":[87],"embeddings":[88],"Models,":[92],"and":[93,111,119,142],"empirically":[95],"assess":[96],"its":[97],"performance":[98,134],"against":[99],"alternative":[100],"combination":[101],"modules.":[102],"We":[103,124],"tested":[104],"our":[105],"approach":[106],"on":[107],"Atari":[109],"games,":[110],"analyzed":[113],"issue":[115],"out-of-distribution":[117],"data":[118],"mitigate":[122],"it.":[123],"showed":[125],"that,":[126],"without":[127],"fine-tuning":[128],"hyperparameters,":[130],"WSA":[131],"obtains":[132],"comparable":[133],"state-of-the-art":[136],"methods.":[137],"This":[138],"method":[139],"is":[140],"effective":[141],"could":[143],"allow":[144],"life-long":[145],"adapt":[149],"scenarios":[152],"over":[153],"time.":[154]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}