{"id":"https://openalex.org/W2979123459","doi":"https://doi.org/10.1109/devlrn.2019.8850685","title":"A Categorization of Reinforcement Learning Exploration Techniques which Facilitates Combination of Different Methods","display_name":"A Categorization of Reinforcement Learning Exploration Techniques which Facilitates Combination of Different Methods","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2979123459","doi":"https://doi.org/10.1109/devlrn.2019.8850685","mag":"2979123459"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2019.8850685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th 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/A5041573273","display_name":"Bj\u00f8rn Ivar Teigen","orcid":null},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Bjorn Ivar Teigen","raw_affiliation_strings":["Department of informatics, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071893221","display_name":"Kai Olav Ellefsen","orcid":"https://orcid.org/0000-0003-2466-2319"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Kai Olav Ellefsen","raw_affiliation_strings":["Department of informatics, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071144214","display_name":"Jim T\u00f8rresen","orcid":"https://orcid.org/0000-0003-0556-0288"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Jim Torresen","raw_affiliation_strings":["Time and Motion, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Time and Motion, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11962521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":null,"first_page":"189","last_page":"194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9954000115394592,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8413987755775452},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7963960766792297},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7854119539260864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5793471932411194},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5599130988121033},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.420604944229126}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8413987755775452},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7963960766792297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854119539260864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5793471932411194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5599130988121033},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.420604944229126},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2019.8850685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th 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":39,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W355724390","https://openalex.org/W779494576","https://openalex.org/W1515933446","https://openalex.org/W1579979603","https://openalex.org/W1600437712","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2039522160","https://openalex.org/W2061868368","https://openalex.org/W2115211925","https://openalex.org/W2121863487","https://openalex.org/W2140332127","https://openalex.org/W2280163991","https://openalex.org/W2417786368","https://openalex.org/W2560647685","https://openalex.org/W2623491082","https://openalex.org/W2751973545","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2962902376","https://openalex.org/W2963007936","https://openalex.org/W2963099933","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2963938771","https://openalex.org/W2964043796","https://openalex.org/W2964291307","https://openalex.org/W4206547457","https://openalex.org/W4234228486","https://openalex.org/W4298857966","https://openalex.org/W4299879948","https://openalex.org/W6638018090","https://openalex.org/W6677067356","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6716474083","https://openalex.org/W6744838376","https://openalex.org/W6747473740"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"The":[0],"exploration":[1,24,45,62,87],"vs.":[2],"exploitation":[3],"problem":[4],"in":[5,36,84],"reinforcement":[6],"learning":[7],"has":[8],"received":[9],"much":[10],"attention":[11],"lately.":[12],"It":[13],"is":[14],"difficult":[15],"to":[16,70],"get":[17],"a":[18,37,42,80,85],"complete":[19],"overview":[20],"of":[21,44,61],"all":[22],"the":[23,49],"methods,":[25],"and":[26,76],"what":[27],"methods":[28,72],"can":[29,31,82],"or":[30],"not":[32],"be":[33],"used":[34],"together":[35],"combined":[38],"algorithm.":[39],"We":[40,67],"propose":[41],"categorization":[43],"techniques":[46,63],"based":[47],"on":[48],"mechanism":[50],"through":[51],"which":[52,89],"they":[53],"generate":[54],"exploratory":[55],"policies.":[56],"This":[57],"enables":[58],"plug-and-play":[59],"combination":[60,81],"from":[64,73],"each":[65,91],"category.":[66],"show":[68],"how":[69],"combine":[71],"different":[74],"categories":[75],"demonstrate":[77],"that":[78],"such":[79],"result":[83],"new":[86],"technique":[88],"outperforms":[90],"individual":[92],"method.":[93]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}