{"id":"https://openalex.org/W7155656177","doi":null,"title":"Maailmanmallinnus ja mustan laatikon optimointi kielimalleilla","display_name":"Maailmanmallinnus ja mustan laatikon optimointi kielimalleilla","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7155656177"},"language":"en","primary_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/143944","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/143944","pdf_url":"https://aaltodoc.aalto.fi/bitstreams/8fa6ee5d-54b9-4ed5-9790-2fe7f1a10eaf/download","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":"G5 Artikkeliv\u00e4it\u00f6skirja"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://aaltodoc.aalto.fi/bitstreams/8fa6ee5d-54b9-4ed5-9790-2fe7f1a10eaf/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097357942","display_name":"Nicola Dainese","orcid":"https://orcid.org/0000-0001-9806-419X","observed_orcids":["https://orcid.org/0000-0001-9806-419X"]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Dainese, Nicola","raw_affiliation_strings":["Department of Computer Science aalto.fi Business , Economy Art, Design, Architecture Science , Technology Crossover"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science aalto.fi Business , Economy Art, Design, Architecture Science , Technology Crossover","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5097357942"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"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":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9574999809265137,"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":0.9574999809265137,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.024700000882148743,"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":0.004000000189989805,"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/world-modeling","display_name":"world modeling","score":0.828000009059906},{"id":"https://openalex.org/keywords/black-box-optimization","display_name":"black-box optimization","score":0.8769999742507935},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9010000228881836},{"id":"https://openalex.org/keywords/program-synthesis","display_name":"program synthesis","score":0.5640000104904175},{"id":"https://openalex.org/keywords/prompt-optimization","display_name":"prompt optimization","score":0.8149999976158142},{"id":"https://openalex.org/keywords/symbolic-regression","display_name":"symbolic regression","score":0.9229999780654907},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.7789999842643738},{"id":"https://openalex.org/keywords/code-generation","display_name":"code generation","score":0.7870000004768372},{"id":"https://openalex.org/keywords/visual-planning","display_name":"visual planning","score":0.8240000009536743},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9819999933242798},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.652999997138977},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.6980000138282776},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6660000085830688},{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.41499999165534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7088000178337097},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6018999814987183},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724000096321106},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.3935999870300293},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35899999737739563},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/143944","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/143944","pdf_url":"https://aaltodoc.aalto.fi/bitstreams/8fa6ee5d-54b9-4ed5-9790-2fe7f1a10eaf/download","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":"G5 Artikkeliv\u00e4it\u00f6skirja"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/143944","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/143944","pdf_url":"https://aaltodoc.aalto.fi/bitstreams/8fa6ee5d-54b9-4ed5-9790-2fe7f1a10eaf/download","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":"G5 Artikkeliv\u00e4it\u00f6skirja"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155656177.pdf","grobid_xml":"https://content.openalex.org/works/W7155656177.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1519072852","https://openalex.org/W1998329127","https://openalex.org/W2242818861","https://openalex.org/W2795843265","https://openalex.org/W2903021817","https://openalex.org/W2993086250","https://openalex.org/W3006576697","https://openalex.org/W3022566517","https://openalex.org/W3118861865","https://openalex.org/W3174770825","https://openalex.org/W3175526646","https://openalex.org/W3177813494","https://openalex.org/W4224912544","https://openalex.org/W4322718191","https://openalex.org/W4389422760","https://openalex.org/W4392872989","https://openalex.org/W4401306886","https://openalex.org/W4402952666","https://openalex.org/W4405434026","https://openalex.org/W4413147844","https://openalex.org/W4415108068","https://openalex.org/W4415796843","https://openalex.org/W4416053382","https://openalex.org/W6929541986"],"related_works":["https://openalex.org/W7117153217","https://openalex.org/W4417282498","https://openalex.org/W4318751399","https://openalex.org/W7163915945","https://openalex.org/W7009943132","https://openalex.org/W7165749951","https://openalex.org/W4384918756","https://openalex.org/W4403364427","https://openalex.org/W4400105126","https://openalex.org/W7133222210"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,12,105,133,175],"reinforcement":[3],"learning":[4],"(RL)":[5],"have":[6],"produced":[7],"agents":[8,56,125,332],"with":[9,89,258,301,310,350],"impressive":[10],"performance":[11,178,275],"domains":[13],"such":[14,91],"as":[15,32,92,113],"video":[16],"and":[17,26,52,95,139,179,198,278,305,319,337,345],"board":[18],"games.":[19],"Yet,":[20],"current":[21],"RL":[22,55],"methods":[23,185,349],"remain":[24],"datainefficient":[25],"generalize":[27],"poorly":[28],"to":[29,120,129,149,210,226,250,291,299],"new":[30,130],"environments,":[31],"they":[33],"typically":[34],"learn":[35,150],"from":[36],"scratch":[37],"without":[38],"leveraging":[39],"prior":[40,59],"knowledge.":[41],"This":[42],"thesis":[43,146,326],"explores":[44],"how":[45,148],"language":[46,73,163],"can":[47,126,334],"improve":[48],"the":[49,69,145,170,173,219,227,230,325,342,351],"sample":[50,180,343],"efficiency":[51,344],"generalization":[53],"of":[54,71,102,116,155,172,177,207,215,229,317,347,353],"by":[57,162,265],"incorporating":[58],"knowledge":[60],"into":[61],"their":[62],"internal":[63,141],"world":[64,107,121,153,241,253,297],"models.":[65,142],"It":[66],"further":[67],"investigates":[68],"use":[70],"large":[72],"models":[74,242,254,298,303],"(LLMs)":[75],"for":[76,188,193,239,261,288],"black-box":[77],"optimization":[78,94,192],"(BBO),":[79],"where":[80,109],"an":[81,156,204],"unknown":[82],"objective":[83],"must":[84],"be":[85],"optimized":[86],"through":[87,339],"trial-and-error,":[88],"applications":[90],"prompt":[93,191,216],"symbolic":[96,199,296,318],"regression.":[97,200],"Finally,":[98,236],"these":[99],"two":[100,189,237],"lines":[101],"work":[103],"converge":[104],"programmatic":[106,240],"models,":[108],"program":[110],"synthesis,":[111],"viewed":[112],"a":[114,151,248,259,286],"form":[115],"BBO,":[117],"is":[118],"applied":[119],"modeling.":[122],"The":[123,201,245,270,283,312],"resulting":[124],"rapidly":[127],"adapt":[128],"tasks":[131],"described":[132],"language,":[134,340],"while":[135,232],"relying":[136],"on":[137],"interpretable":[138,280],"verifiable":[140],"To":[143],"begin,":[144],"demonstrates":[147],"stochastic":[152],"model":[154],"environment":[157],"exhibiting":[158],"novel":[159],"dynamics,":[160],"accompanied":[161],"descriptions":[164],"at":[165],"test":[166],"time,":[167],"improving":[168],"over":[169,276],"state":[171,228],"art":[174,231],"terms":[176],"efficiency.":[181],"Next,":[182],"LLM-based":[183],"BBO":[184],"are":[186,243],"developed":[187],"tasks:":[190],"code,":[194],"via":[195,255],"docstring":[196,211],"reformulation,":[197],"former":[202],"exposes":[203],"unexpected":[205],"robustness":[206],"open-source":[208],"LLMs":[209],"changes,":[212],"revealing":[213],"limits":[214],"optimization,":[217],"whereas":[218],"latter":[220],"achieves":[221,272],"comparable":[222],"or":[223],"superior":[224,273],"results":[225,313],"producing":[233],"simpler":[234],"formulas.":[235],"approaches":[238,293,306],"considered.":[244],"first":[246],"presents":[247],"framework":[249],"generate":[251],"code":[252,262],"LLMs,":[256],"together":[257],"method":[260],"generation":[263],"guided":[264],"Monte":[266],"Carlo":[267],"Tree":[268],"Search.":[269],"approach":[271],"coding":[274],"baselines":[277],"faster,":[279],"planning":[281],"agents.":[282],"second":[284],"proposes":[285],"benchmark":[287],"visual":[289],"planning,":[290],"compare":[292],"that":[294,307,333],"ground":[295],"observations":[300],"vision-language":[302],"(VLMs)":[304],"plan":[308],"directly":[309],"VLMs.":[311],"reveal":[314],"complementary":[315],"strengths":[316],"direct":[320],"VLM-based":[321],"planning.":[322],"Taken":[323],"together,":[324],"contributions":[327],"mark":[328],"progress":[329],"toward":[330],"autonomous":[331],"reason,":[335],"plan,":[336],"optimize":[338],"combining":[341],"interpretability":[346],"modelbased":[348],"flexibility":[352],"LLMs.":[354]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-04-26T00:00:00"}