{"id":"https://openalex.org/W3136265295","doi":"https://doi.org/10.1109/iros51168.2021.9636536","title":"Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model","display_name":"Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3136265295","doi":"https://doi.org/10.1109/iros51168.2021.9636536","mag":"3136265295"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636536","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.08255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020240470","display_name":"Thanh Nguyen","orcid":"https://orcid.org/0000-0003-3533-4054"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Thanh Nguyen","raw_affiliation_strings":["Faculty of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028393159","display_name":"Tung M. Luu","orcid":"https://orcid.org/0000-0001-9488-7463"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tung M. Luu","raw_affiliation_strings":["Faculty of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059033571","display_name":"Thang Vu","orcid":"https://orcid.org/0000-0003-0486-6349"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Thang Vu","raw_affiliation_strings":["Faculty of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["Faculty of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020240470"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.5238,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.85561201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3471","last_page":"3477"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9937999844551086,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9890999794006348,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.861912727355957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7952011823654175},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7149897813796997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7019064426422119},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6231968402862549},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5726555585861206},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5388365387916565},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.5152001976966858},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.512612521648407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44816893339157104},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42863649129867554},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11890646815299988}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.861912727355957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952011823654175},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7149897813796997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7019064426422119},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6231968402862549},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5726555585861206},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5388365387916565},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.5152001976966858},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.512612521648407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44816893339157104},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42863649129867554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11890646815299988},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros51168.2021.9636536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636536","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.08255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.08255","pdf_url":"https://arxiv.org/pdf/2103.08255","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.08255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.08255","pdf_url":"https://arxiv.org/pdf/2103.08255","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":92,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2101524054","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155007355","https://openalex.org/W2173248099","https://openalex.org/W2195446438","https://openalex.org/W2257979135","https://openalex.org/W2551887912","https://openalex.org/W2553347458","https://openalex.org/W2561776174","https://openalex.org/W2596982695","https://openalex.org/W2738669288","https://openalex.org/W2751973545","https://openalex.org/W2772709170","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2787236409","https://openalex.org/W2789824229","https://openalex.org/W2798991696","https://openalex.org/W2823112946","https://openalex.org/W2842511635","https://openalex.org/W2885550588","https://openalex.org/W2890208753","https://openalex.org/W2899205164","https://openalex.org/W2900152462","https://openalex.org/W2904455790","https://openalex.org/W2905606790","https://openalex.org/W2920362155","https://openalex.org/W2949475445","https://openalex.org/W2950872548","https://openalex.org/W2951004968","https://openalex.org/W2953072278","https://openalex.org/W2954974210","https://openalex.org/W2962872206","https://openalex.org/W2963160877","https://openalex.org/W2963276097","https://openalex.org/W2963484919","https://openalex.org/W2963523627","https://openalex.org/W2963634205","https://openalex.org/W2963864421","https://openalex.org/W2963985863","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2964067469","https://openalex.org/W2964161785","https://openalex.org/W2964342357","https://openalex.org/W2971040589","https://openalex.org/W2977481643","https://openalex.org/W2981030070","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2994073215","https://openalex.org/W2994714051","https://openalex.org/W2995298643","https://openalex.org/W3005680577","https://openalex.org/W3009561768","https://openalex.org/W3021708257","https://openalex.org/W3023640063","https://openalex.org/W3035524453","https://openalex.org/W3036619998","https://openalex.org/W3098053103","https://openalex.org/W3103780890","https://openalex.org/W3115293622","https://openalex.org/W3118210634","https://openalex.org/W4287811291","https://openalex.org/W4288294128","https://openalex.org/W4288320194","https://openalex.org/W4289294484","https://openalex.org/W4293396018","https://openalex.org/W4297744728","https://openalex.org/W4297797010","https://openalex.org/W4297808394","https://openalex.org/W4300799055","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6729556111","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6740801417","https://openalex.org/W6741977017","https://openalex.org/W6747473740","https://openalex.org/W6748638692","https://openalex.org/W6753060773","https://openalex.org/W6756256016","https://openalex.org/W6760405395","https://openalex.org/W6765242767","https://openalex.org/W6771217966","https://openalex.org/W6775634482","https://openalex.org/W6776867236","https://openalex.org/W6910476156"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370"],"abstract_inverted_index":{"Developing":[0],"an":[1],"agent":[2,124],"in":[3,143],"reinforcement":[4],"learning":[5,46,77,145],"(RL)":[6],"that":[7],"is":[8,23],"capable":[9],"of":[10,39,121,158,170],"performing":[11],"complex":[12],"control":[13],"tasks":[14],"directly":[15,63],"from":[16],"high-dimensional":[17],"observation":[18],"such":[19,163],"as":[20,26,164],"raw":[21,65],"pixels":[22],"a":[24,45,49,58,69,97],"challenge":[25],"efforts":[27],"still":[28],"need":[29],"to":[30,56,78,88,95,125],"be":[31],"made":[32],"towards":[33],"improving":[34],"sample":[35,99,150],"efficiency":[36,100,151],"and":[37,74,92,117,130,139],"generalization":[38,155],"RL":[40,61,123,161,176],"algorithm.":[41],"This":[42],"paper":[43],"considers":[44],"framework":[47],"for":[48,101],"Curiosity":[50],"Contrastive":[51],"Forward":[52],"Dynamics":[53],"Model":[54],"(CCFDM)":[55],"achieve":[57,96],"more":[59,98],"sample-efficient":[60],"based":[62,112],"on":[64,113,168,178],"pixels.":[66],"CCFDM":[67,107,171],"incorporates":[68],"forward":[70],"dynamics":[71],"model":[72],"(FDM)":[73],"performs":[75],"contrastive":[76,144],"train":[79],"its":[80],"deep":[81],"convolutional":[82],"neural":[83],"network-based":[84],"image":[85],"encoder":[86],"(IE)":[87],"extract":[89],"conducive":[90],"spatial":[91],"temporal":[93],"information":[94],"RL.":[102],"In":[103],"addition,":[104],"during":[105],"training,":[106],"provides":[108],"intrinsic":[109],"rewards,":[110],"produced":[111],"FDM":[114],"prediction":[115],"error,":[116],"encourages":[118],"the":[119,122,149,154,179],"curiosity":[120],"improve":[126,146],"exploration.":[127],"The":[128],"diverge":[129],"less-repetitive":[131],"observations":[132],"provided":[133],"by":[134],"both":[135],"our":[136],"exploration":[137],"strategy":[138],"data":[140],"augmentation":[141],"available":[142],"not":[147],"only":[148],"but":[152],"also":[153],".":[156],"Performance":[157],"existing":[159],"model-free":[160],"methods":[162,177],"Soft":[165],"Actor-Critic":[166],"built":[167],"top":[169],"outperforms":[172],"prior":[173],"state-of-the-art":[174],"pixel-based":[175],"DeepMind":[180],"Control":[181],"Suite":[182],"benchmark.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2021-03-29T00:00:00"}