{"id":"https://openalex.org/W4389666710","doi":"https://doi.org/10.1109/iros55552.2023.10342018","title":"Sample-Efficient Real-Time Planning with Curiosity Cross-Entropy Method and Contrastive Learning","display_name":"Sample-Efficient Real-Time Planning with Curiosity Cross-Entropy Method and Contrastive Learning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666710","doi":"https://doi.org/10.1109/iros55552.2023.10342018"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342018","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10342018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5108885415","display_name":"Mostafa Kotb","orcid":null},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mostafa Kotb","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108885415"],"corresponding_institution_ids":["https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":0.6613,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76365225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"9456","last_page":"9463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9904999732971191,"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"}},{"id":"https://openalex.org/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7620600461959839},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.6825051307678223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6332166790962219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6144217848777771},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5280410051345825},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.49406054615974426},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.46327850222587585},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4125567376613617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20519864559173584},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.16739588975906372},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12455326318740845}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7620600461959839},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.6825051307678223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6332166790962219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6144217848777771},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5280410051345825},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.49406054615974426},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.46327850222587585},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4125567376613617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20519864559173584},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.16739588975906372},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12455326318740845},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342018","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10342018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/13","score":0.4699999988079071,"display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G6276684567","display_name":null,"funder_award_id":"TRR 169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1577352482","https://openalex.org/W1583837637","https://openalex.org/W2101524054","https://openalex.org/W2138621090","https://openalex.org/W2160589914","https://openalex.org/W2257979135","https://openalex.org/W2417786368","https://openalex.org/W2885550588","https://openalex.org/W2898417779","https://openalex.org/W2911296969","https://openalex.org/W2950564923","https://openalex.org/W2953070460","https://openalex.org/W2962730405","https://openalex.org/W2962872206","https://openalex.org/W2963099939","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W3015437096","https://openalex.org/W3035060554","https://openalex.org/W3036619998","https://openalex.org/W3045217911","https://openalex.org/W3092161856","https://openalex.org/W3095669803","https://openalex.org/W3101480866","https://openalex.org/W3104462930","https://openalex.org/W3136265295","https://openalex.org/W3206042616","https://openalex.org/W3207342878","https://openalex.org/W4206033892","https://openalex.org/W4288320194","https://openalex.org/W4296555334","https://openalex.org/W4297808394","https://openalex.org/W4298206671","https://openalex.org/W4320858069","https://openalex.org/W6683436435","https://openalex.org/W6685757253","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6733814495","https://openalex.org/W6735033012","https://openalex.org/W6747473740","https://openalex.org/W6751494529","https://openalex.org/W6753925943","https://openalex.org/W6756256016","https://openalex.org/W6762863188","https://openalex.org/W6763990646","https://openalex.org/W6765242767","https://openalex.org/W6771217966","https://openalex.org/W6778000925","https://openalex.org/W6779326418","https://openalex.org/W6780226713","https://openalex.org/W6780470247","https://openalex.org/W6780523241","https://openalex.org/W6782858274","https://openalex.org/W6783582377","https://openalex.org/W6785204124","https://openalex.org/W6785996349","https://openalex.org/W6787713516","https://openalex.org/W6795793241","https://openalex.org/W6803185011","https://openalex.org/W6809990427","https://openalex.org/W6843397648","https://openalex.org/W6844194202","https://openalex.org/W6849581600"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4383268304"],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1],"learning":[2,144],"(MBRL)":[3],"with":[4,178],"real-time":[5],"planning":[6,20,50,62,65,115],"has":[7],"shown":[8],"great":[9],"potential":[10],"in":[11,71,117],"locomotion":[12],"and":[13,128,175],"manipulation":[14],"control":[15,154],"tasks.":[16],"However,":[17],"the":[18,24,38,44,56,61,67,72,93,105,114,125,157,179],"existing":[19],"methods,":[21],"such":[22],"as":[23,48],"Cross-Entropy":[25],"Method":[26],"(CEM),":[27],"do":[28],"not":[29],"scale":[30],"well":[31],"to":[32,54,79,133,145],"complex":[33],"high-dimensional":[34],"environments.":[35],"One":[36],"of":[37,46,74,92,107],"key":[39],"reasons":[40],"for":[41,96],"underperformance":[42],"is":[43,164],"lack":[45],"exploration,":[47],"these":[49,119],"methods":[51],"only":[52],"aim":[53],"maximize":[55],"cumulative":[57],"extrinsic":[58,127],"reward":[59],"over":[60,113],"horizon.":[63],"Furthermore,":[64],"inside":[66],"compact":[68],"latent":[69,148],"space":[70],"absence":[73],"observations":[75],"makes":[76],"it":[77],"challenging":[78],"use":[80],"curiosity-based":[81],"intrinsic":[82,129],"motivation.":[83],"We":[84],"propose":[85],"Curiosity":[86],"CEM":[87,94],"(CCEM),":[88],"an":[89],"improved":[90],"version":[91],"algorithm":[95],"encouraging":[97,132],"exploration":[98],"via":[99],"curiosity.":[100],"Our":[101],"proposed":[102],"method":[103],"maximizes":[104],"sum":[106],"state-action":[108],"<tex":[109,120],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[110,121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$Q$</tex>":[111,122],"values":[112,123],"horizon,":[116],"which":[118],"estimate":[124],"future":[126],"reward,":[130],"hence":[131],"reach":[134],"novel":[135],"observations.":[136],"In":[137],"addition,":[138],"our":[139],"model":[140],"uses":[141],"contrastive":[142],"representation":[143],"efficiently":[146],"learn":[147],"representations.":[149],"Experiments":[150],"on":[151],"image-based":[152],"continuous":[153],"tasks":[155],"from":[156],"DeepMind":[158],"Control":[159],"suite":[160],"show":[161],"that":[162],"CCEM":[163],"by":[165],"a":[166],"large":[167],"margin":[168],"more":[169],"sample-efficient":[170],"than":[171],"previous":[172],"MBRL":[173],"algorithms":[174],"compares":[176],"favorably":[177],"best":[180],"model-free":[181],"RL":[182],"methods.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-27T09:02:27.158192","created_date":"2025-10-10T00:00:00"}