{"id":"https://openalex.org/W7143053609","doi":"https://doi.org/10.5555/3709347.3743973","title":"Predictive Improvement through Latent Space Optimisation","display_name":"Predictive Improvement through Latent Space Optimisation","publication_year":2025,"publication_date":"2025-06-05","ids":{"openalex":"https://openalex.org/W7143053609","doi":"https://doi.org/10.5555/3709347.3743973"},"language":"en","primary_location":{"id":"pmh:oai:openaccess.city.ac.uk:34702","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/e=2Ealonso.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/34702/1/McCaffreyAlonsoMondragon.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"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":"PeerReviewed"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://openaccess.city.ac.uk/id/eprint/34702/1/McCaffreyAlonsoMondragon.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130871307","display_name":"A. McCaffrey","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"McCaffrey, A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130906594","display_name":"E. Alonso","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alonso, E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130897728","display_name":"E. Mondrag\u00f3n","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mondrag\u00f3n, E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5130871307"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8594132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.8240000009536743,"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":0.8240000009536743,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0210999995470047,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.016599999740719795,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/robustness","display_name":"Robustness (evolution)","score":0.6384999752044678},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5684999823570251},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5288000106811523},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.38029998540878296},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.3003999888896942}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6384999752044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6044999957084656},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5684999823570251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5501999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5407999753952026},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:openaccess.city.ac.uk:34702","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/e=2Ealonso.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/34702/1/McCaffreyAlonsoMondragon.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"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":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:openaccess.city.ac.uk:34702","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/e=2Ealonso.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/34702/1/McCaffreyAlonsoMondragon.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"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":"PeerReviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7143053609.pdf","grobid_xml":"https://content.openalex.org/works/W7143053609.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"exploration":[1],"remains":[2],"a":[3],"challenge":[4],"in":[5,10,35,63],"reinforcement":[6],"learning":[7],"(RL),":[8],"especially":[9],"stochastic":[11,76],"or":[12],"complex":[13],"environments.":[14],"We":[15],"introduce":[16],"Predictive":[17],"Improvement":[18],"through":[19],"Latent":[20],"space":[21],"OpTimisation":[22],"(PILOT),":[23],"an":[24,43],"intrinsically":[25],"motivated":[26],"RL":[27],"algorithm":[28],"that":[29,67],"rewards":[30],"actions":[31],"leading":[32],"to":[33,75],"improvements":[34],"the":[36],"agent\u2019s":[37],"environmental":[38],"dynamics":[39],"model.":[40],"PILOT":[41,68],"optimizes":[42],"intrinsic":[44,60],"reward":[45],"signal":[46],"based":[47],"on":[48],"epistemic":[49],"uncertainty":[50],"reduction,":[51],"thereby":[52],"encouraging":[53],"structured":[54],"exploration.":[55],"Our":[56],"evaluations":[57],"against":[58],"benchmark":[59],"motivation":[61],"algorithms":[62],"challenging":[64],"environments":[65],"show":[66],"achieves":[69],"superior":[70],"performance":[71],"and":[72],"exhibits":[73],"robustness":[74],"distractions.":[77]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2026-03-30T00:00:00"}