{"id":"https://openalex.org/W2795659854","doi":"https://doi.org/10.1109/devlrn.2017.8329806","title":"A growing multi-expert structure for open-ended unsupervised learning of sensory state spaces","display_name":"A growing multi-expert structure for open-ended unsupervised learning of sensory state spaces","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2795659854","doi":"https://doi.org/10.1109/devlrn.2017.8329806","mag":"2795659854"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2017.8329806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-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/A5029201378","display_name":"Matthias Kubisch","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Kubisch","raw_affiliation_strings":["Computer Science Department, Humboldt-Universit\u00e4t zu Berlin"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Humboldt-Universit\u00e4t zu Berlin","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5029201378"],"corresponding_institution_ids":["https://openalex.org/I39343248"],"apc_list":null,"apc_paid":null,"fwci":0.195,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65658945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9988999962806702,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9988999962806702,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7441083192825317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7133944034576416},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6606522798538208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5820233821868896},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5498698353767395},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5206865072250366},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49842166900634766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49391990900039673},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.48974061012268066},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.41096171736717224},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14971628785133362},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1461986005306244}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7441083192825317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7133944034576416},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6606522798538208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5820233821868896},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5498698353767395},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5206865072250366},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49842166900634766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49391990900039673},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.48974061012268066},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.41096171736717224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14971628785133362},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1461986005306244},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2017.8329806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W169326478","https://openalex.org/W1556936384","https://openalex.org/W1560851313","https://openalex.org/W2061868368","https://openalex.org/W2091351095","https://openalex.org/W2096387789","https://openalex.org/W2101524054","https://openalex.org/W2121863487","https://openalex.org/W2139333458","https://openalex.org/W2185417612","https://openalex.org/W2266352350","https://openalex.org/W2402252322","https://openalex.org/W4214717370","https://openalex.org/W4252105577","https://openalex.org/W6686542590","https://openalex.org/W6693377735","https://openalex.org/W6713228029"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W3203657119","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,57,72,78,88,108],"new":[3],"algorithm,":[4],"called":[5],"Growing":[6],"Multi-Expert":[7],"Structure":[8],"(GMES)":[9],"for":[10,28],"unsupervised":[11],"learning":[12,20,32,84,105],"of":[13,65,74,111,118],"discrete":[14],"state":[15,30,67],"spaces":[16],"in":[17,71],"open-ended":[18],"reinforcement":[19],"tasks.":[21],"The":[22,63],"proposed":[23],"incremental":[24],"algorithm":[25],"is":[26,69],"suitable":[27],"on-line":[29],"space":[31,68],"on":[33],"small-scale":[34],"adaptive":[35],"systems":[36],"due":[37],"to":[38,60,113],"its":[39,52],"low":[40],"computational":[41],"requirements.":[42],"It":[43],"directly":[44],"processes":[45],"sequential,":[46],"raw":[47],"sensory":[48],"data,":[49],"can":[50],"follow":[51],"non-stationarity,":[53],"and":[54],"needs":[55],"only":[56],"few":[58],"parameters":[59],"be":[61],"tuned.":[62],"development":[64],"the":[66,94,103,115],"demonstrated":[70],"set":[73],"RL":[75],"experiments":[76],"using":[77],"physically":[79],"simulated":[80],"pendulum":[81],"with":[82],"varying":[83],"goals":[85],"started":[86],"from":[87,97],"tabula-rasa-situation.":[89],"Furthermore,":[90],"we":[91],"show":[92],"that":[93],"system":[95],"benefits":[96],"intrinsic":[98],"motivation":[99],"by":[100],"feeding":[101],"back":[102],"measured":[104],"progress":[106],"as":[107],"separate":[109],"source":[110],"reward":[112],"improve":[114],"system's":[116],"capabilities":[117],"self-exploration.":[119]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}