{"id":"https://openalex.org/W3132615417","doi":"https://doi.org/10.1109/iros45743.2020.9341014","title":"Exploration Strategy based on Validity of Actions in Deep Reinforcement Learning","display_name":"Exploration Strategy based on Validity of Actions in Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3132615417","doi":"https://doi.org/10.1109/iros45743.2020.9341014","mag":"3132615417"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5084346572","display_name":"Hyung-Suk Yoon","orcid":"https://orcid.org/0000-0002-9976-139X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyung-Suk Yoon","raw_affiliation_strings":["Seoul National University, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444575","display_name":"Sang-Hyun Lee","orcid":"https://orcid.org/0009-0007-3360-4758"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hyun Lee","raw_affiliation_strings":["Seoul National University, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048311228","display_name":"Seung\u2010Woo Seo","orcid":"https://orcid.org/0000-0003-4890-8563"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Woo Seo","raw_affiliation_strings":["Seoul National University, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084346572"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20710171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"abs 1707 6347","issue":null,"first_page":"6134","last_page":"6139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9750999808311462,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7916702628135681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719669342041016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5824344158172607},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5163675546646118},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4896579384803772},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4657882750034332},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.42619869112968445},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4164014458656311},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09886360168457031},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09199395775794983}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7916702628135681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719669342041016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5824344158172607},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5163675546646118},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4896579384803772},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4657882750034332},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.42619869112968445},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4164014458656311},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09886360168457031},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09199395775794983},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/iros45743.2020.9341014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8199999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1520997877","https://openalex.org/W1757796397","https://openalex.org/W2099471712","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2161966552","https://openalex.org/W2342840547","https://openalex.org/W2489939061","https://openalex.org/W2561776174","https://openalex.org/W2736601468","https://openalex.org/W2787800669","https://openalex.org/W2893359011","https://openalex.org/W2949475445","https://openalex.org/W2962867954","https://openalex.org/W2962894046","https://openalex.org/W2963276097","https://openalex.org/W2963277051","https://openalex.org/W2963523627","https://openalex.org/W2964112890","https://openalex.org/W3091492359","https://openalex.org/W4285719527","https://openalex.org/W4295719664","https://openalex.org/W4298857966","https://openalex.org/W4320013936","https://openalex.org/W6637967152","https://openalex.org/W6682849425","https://openalex.org/W6683603353","https://openalex.org/W6717230150","https://openalex.org/W6718092244","https://openalex.org/W6720501231","https://openalex.org/W6730641667","https://openalex.org/W6741002519","https://openalex.org/W6745935785","https://openalex.org/W6755160885"],"related_works":["https://openalex.org/W3034924094","https://openalex.org/W3094954546","https://openalex.org/W1488708774","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"How":[0],"to":[1,43,53,90,104,124,143,147,173,191,196],"explore":[2,55,125],"environments":[3,128],"is":[4,38,89,131],"one":[5],"of":[6,14,51,94,101,110,199],"the":[7,12,92],"most":[8],"critical":[9],"factors":[10],"for":[11,40],"performance":[13],"an":[15,41,122,145,189],"agent":[16,42,123,146,190],"in":[17,63,108,127],"reinforcement":[18,64],"learning.":[19,65,159],"Conventional":[20],"exploration":[21,29,74,112,155,163,186],"strategies":[22],"such":[23],"as":[24],"\u03b5-greedy":[25],"algorithm":[26],"and":[27,48,113],"Gaussian":[28],"noise":[30],"simply":[31],"depend":[32],"on":[33,80,165],"pure":[34],"randomness.":[35],"However,":[36],"it":[37],"required":[39],"consider":[44],"its":[45],"training":[46],"progress":[47],"long-term":[49],"usefulness":[50],"actions":[52,78,95,107],"efficiently":[54,126],"complex":[56],"environments,":[57],"which":[58],"remains":[59],"a":[60,72,118],"major":[61],"challenge":[62],"To":[66],"address":[67],"this":[68],"challenge,":[69],"we":[70],"propose":[71],"novel":[73],"method":[75,88],"that":[76,120,184],"selects":[77],"based":[79],"their":[81],"validity.":[82],"The":[83,138,181],"key":[84],"idea":[85],"behind":[86],"our":[87,154,162,185],"estimate":[91],"validity":[93,198],"by":[96,152],"leveraging":[97],"zero":[98],"avoiding":[99],"property":[100],"kullback-leibler":[102],"divergence":[103],"comprehensively":[105],"evaluate":[106],"terms":[109],"both":[111],"exploitation.":[114],"We":[115,160],"also":[116],"introduce":[117],"framework":[119,139],"allows":[121],"where":[129],"reward":[130],"sparse":[132],"or":[133],"cannot":[134],"be":[135],"defined":[136],"intuitively.":[137],"uses":[140],"expert":[141],"demonstrations":[142],"guide":[144],"visit":[148,192],"task-relevant":[149,193],"state":[150,194],"space":[151,195],"combining":[153],"strategy":[156,164,187],"with":[157],"imitation":[158],"demonstrate":[161],"several":[166,202],"tasks":[167,172],"ranging":[168],"from":[169],"classical":[170],"control":[171],"high-dimensional":[174],"urban":[175],"autonomous":[176],"driving":[177],"scenarios":[178],"at":[179],"roundabout.":[180],"results":[182],"show":[183],"encourages":[188],"enhance":[197],"actions,":[200],"outperforming":[201],"previous":[203],"methods.":[204]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}