{"id":"https://openalex.org/W3201916245","doi":"https://doi.org/10.1109/icra46639.2022.9811663","title":"Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning","display_name":"Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W3201916245","doi":"https://doi.org/10.1109/icra46639.2022.9811663","mag":"3201916245"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811663","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","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/A5065108843","display_name":"Elie Aljalbout","orcid":"https://orcid.org/0000-0003-0590-0043"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Elie Aljalbout","raw_affiliation_strings":["Technical University of Munich (TUM),Munich,Germany,80797"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (TUM),Munich,Germany,80797","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019981077","display_name":"Maximilian Ulmer","orcid":null},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Ulmer","raw_affiliation_strings":["Technical University of Munich (TUM),Munich,Germany,80797","German Aerospace Center, Insitute of Robotics and Mechatronics, Wessling, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (TUM),Munich,Germany,80797","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"German Aerospace Center, Insitute of Robotics and Mechatronics, Wessling, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050478468","display_name":"Rudolph Triebel","orcid":"https://orcid.org/0000-0002-7975-036X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rudolph Triebel","raw_affiliation_strings":["Technical University of Munich (TUM),Munich,Germany,80797","German Aerospace Center, Insitute of Robotics and Mechatronics, Wessling, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (TUM),Munich,Germany,80797","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"German Aerospace Center, Insitute of Robotics and Mechatronics, Wessling, Germany","institution_ids":["https://openalex.org/I2898391981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065108843"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.36425339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"3591","last_page":"3597"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976999759674072,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9927999973297119,"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":0.8233574032783508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7349292039871216},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6567741632461548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6261560916900635},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6089729070663452},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6036514043807983},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.5677357912063599},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5460290312767029},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.468049019575119},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.44609951972961426},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4292057752609253},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.410396933555603},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1138795018196106},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06592273712158203}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8233574032783508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7349292039871216},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6567741632461548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6261560916900635},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6089729070663452},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6036514043807983},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.5677357912063599},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5460290312767029},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.468049019575119},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.44609951972961426},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4292057752609253},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.410396933555603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1138795018196106},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06592273712158203},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811663","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W117096852","https://openalex.org/W834081922","https://openalex.org/W1164749991","https://openalex.org/W1522301498","https://openalex.org/W1863227302","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2121863487","https://openalex.org/W2154997814","https://openalex.org/W2280163991","https://openalex.org/W2321533354","https://openalex.org/W2417786368","https://openalex.org/W2567455162","https://openalex.org/W2596982695","https://openalex.org/W2751973545","https://openalex.org/W2753738274","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2787666871","https://openalex.org/W2790924949","https://openalex.org/W2798991696","https://openalex.org/W2842511635","https://openalex.org/W2900152462","https://openalex.org/W2927928207","https://openalex.org/W2932108515","https://openalex.org/W2944828972","https://openalex.org/W2962902376","https://openalex.org/W2963160877","https://openalex.org/W2963276097","https://openalex.org/W2963430173","https://openalex.org/W2963523627","https://openalex.org/W2963809228","https://openalex.org/W2963938771","https://openalex.org/W2964067469","https://openalex.org/W2964121744","https://openalex.org/W2968095426","https://openalex.org/W2970971581","https://openalex.org/W2977481643","https://openalex.org/W3015437096","https://openalex.org/W3035058308","https://openalex.org/W3085605093","https://openalex.org/W3089931053","https://openalex.org/W3095452501","https://openalex.org/W3102186490","https://openalex.org/W3115293622","https://openalex.org/W3131871335","https://openalex.org/W3168856269","https://openalex.org/W3202960171","https://openalex.org/W4214717370","https://openalex.org/W4286955635","https://openalex.org/W4287626351","https://openalex.org/W4287667696","https://openalex.org/W4288376404","https://openalex.org/W4289294484","https://openalex.org/W4295312788","https://openalex.org/W4297744728","https://openalex.org/W4297808394","https://openalex.org/W4320013936","https://openalex.org/W6604803494","https://openalex.org/W6623316541","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6695011786","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6735033012","https://openalex.org/W6741977017","https://openalex.org/W6744627333","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6750782655","https://openalex.org/W6756256016","https://openalex.org/W6756303580","https://openalex.org/W6760514122","https://openalex.org/W6761222500","https://openalex.org/W6762573206","https://openalex.org/W6766978945","https://openalex.org/W6768511085","https://openalex.org/W6782858274","https://openalex.org/W6784930079","https://openalex.org/W6785684253","https://openalex.org/W6791110673","https://openalex.org/W6801750468"],"related_works":["https://openalex.org/W4361193280","https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W3147214434","https://openalex.org/W3207509264","https://openalex.org/W4288754364","https://openalex.org/W3027305282","https://openalex.org/W2989021453","https://openalex.org/W3036553387","https://openalex.org/W4288027505"],"abstract_inverted_index":{"Vision-based":[0],"reinforcement":[1],"learning":[2,43],"(RL)":[3],"is":[4],"a":[5,55,80],"promising":[6],"approach":[7,109,140],"to":[8,36,65,110,178],"solve":[9],"control":[10],"tasks":[11],"involving":[12],"images":[13],"as":[14],"the":[15,47,72,85,92,121,131,142,148,154,168,180,183],"main":[16],"observation.":[17],"State-of-the-art":[18],"RL":[19,48,125],"algorithms":[20],"still":[21],"struggle":[22],"in":[23,51,58],"terms":[24],"of":[25,69,74,87,95,124,130,144],"sample":[26,59,93,112,188],"efficiency,":[27],"especially":[28],"when":[29],"using":[30],"image":[31],"observations.":[32],"This":[33],"has":[34],"led":[35],"increased":[37],"attention":[38],"on":[39],"integrating":[40],"state":[41,115,150],"representation":[42,116],"(SRL)":[44],"techniques":[45],"into":[46],"pipeline.":[49],"Work":[50],"this":[52,70,104],"field":[53],"demonstrates":[54],"substantial":[56],"improvement":[57],"efficiency":[60,94],"among":[61],"other":[62],"benefits.":[63],"However,":[64],"take":[66],"full":[67],"advantage":[68,129],"paradigm,":[71],"quality":[73],"samples":[75,89],"used":[76],"for":[77,114,156,165],"training":[78],"plays":[79],"crucial":[81],"role.":[82],"More":[83],"importantly,":[84],"diversity":[86,113],"these":[88],"could":[90],"affect":[91],"vision-based":[96],"RL,":[97],"but":[98],"also":[99],"its":[100],"generalization":[101],"capability.":[102],"In":[103,172],"work,":[105],"we":[106],"present":[107],"an":[108],"improve":[111],"learning.":[117],"Our":[118,134],"method":[119,176],"enhances":[120],"exploration":[122],"capability":[123],"algorithms,":[126],"by":[127],"taking":[128],"SRL":[132],"setup.":[133],"experiments":[135],"show":[136],"that":[137],"our":[138,175],"proposed":[139],"boosts":[141],"visitation":[143],"problematic":[145],"states,":[146],"improves":[147],"learned":[149],"representation,":[151],"and":[152,186],"outperforms":[153],"baselines":[155],"all":[157],"tested":[158],"environments.":[159],"These":[160],"results":[161],"are":[162],"most":[163],"apparent":[164],"environments":[166],"where":[167],"baseline":[169],"methods":[170],"struggle.":[171],"simple":[173],"environments,":[174],"contributes":[177],"stabilizing":[179],"training,":[181],"reducing":[182],"reward":[184],"variance,":[185],"improving":[187],"efficiency.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}