{"id":"https://openalex.org/W4389666555","doi":"https://doi.org/10.1109/iros55552.2023.10342272","title":"Learning to Solve Tasks with Exploring Prior Behaviours","display_name":"Learning to Solve Tasks with Exploring Prior Behaviours","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666555","doi":"https://doi.org/10.1109/iros55552.2023.10342272"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342272","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":"conference-paper","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/A5065420714","display_name":"Ruiqi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruiqi Zhu","raw_affiliation_strings":["King's College London,Department of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London,Department of Engineering","institution_ids":["https://openalex.org/I4210119896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406638","display_name":"Siyuan Li","orcid":"https://orcid.org/0000-0002-9999-437X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084139877","display_name":"Tianhong Dai","orcid":"https://orcid.org/0000-0001-8904-1551"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tianhong Dai","raw_affiliation_strings":["University of Aberdeen,Department of Computing Science","Department of Computing Science, University of Aberdeen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Aberdeen,Department of Computing Science","institution_ids":["https://openalex.org/I195460627"]},{"raw_affiliation_string":"Department of Computing Science, University of Aberdeen","institution_ids":["https://openalex.org/I195460627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010176958","display_name":"Chongjie Zhang","orcid":"https://orcid.org/0000-0001-8068-0162"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongjie Zhang","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059459055","display_name":"Oya \u00c7eliktutan","orcid":"https://orcid.org/0000-0002-7213-6359"},"institutions":[{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oya Celiktutan","raw_affiliation_strings":["King's College London,Department of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London,Department of Engineering","institution_ids":["https://openalex.org/I4210119896"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7501","last_page":"7507"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.994700014591217,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9516000151634216,"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/task","display_name":"Task (project management)","score":0.8165872693061829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7968347072601318},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6654217839241028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5980657935142517},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.526591956615448},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5170412659645081},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4877260625362396},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4800656735897064},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4340517520904541},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3856697082519531},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06643858551979065}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.8165872693061829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968347072601318},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6654217839241028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5980657935142517},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.526591956615448},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5170412659645081},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4877260625362396},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4800656735897064},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4340517520904541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3856697082519531},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06643858551979065},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342272","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2938421504","https://openalex.org/W2963277051","https://openalex.org/W2963411833","https://openalex.org/W2963523627","https://openalex.org/W3097907450","https://openalex.org/W3113190209","https://openalex.org/W3127561923","https://openalex.org/W3136265295","https://openalex.org/W3192471089","https://openalex.org/W4223568377","https://openalex.org/W4240805545","https://openalex.org/W4287257196","https://openalex.org/W4300799055","https://openalex.org/W6640174482","https://openalex.org/W6683001934","https://openalex.org/W6684921986","https://openalex.org/W6718092244","https://openalex.org/W6735033012","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6756303580","https://openalex.org/W6771807793","https://openalex.org/W6771968188","https://openalex.org/W6779780899","https://openalex.org/W6785279338","https://openalex.org/W6785353143","https://openalex.org/W6785876034","https://openalex.org/W6787998924","https://openalex.org/W6792301857","https://openalex.org/W6796242396","https://openalex.org/W6798895900","https://openalex.org/W6840258811"],"related_works":["https://openalex.org/W2732813147","https://openalex.org/W2110944602","https://openalex.org/W3213722473","https://openalex.org/W2143460112","https://openalex.org/W1564680838","https://openalex.org/W2060591604","https://openalex.org/W2003125260","https://openalex.org/W2166791242","https://openalex.org/W3012440055","https://openalex.org/W2967461658"],"abstract_inverted_index":{"Demonstrations":[0],"are":[1,41,156],"widely":[2],"used":[3],"in":[4,19,62,85,120],"Deep":[5],"Reinforcement":[6],"Learning":[7],"(DRL)":[8],"for":[9,45],"facilitating":[10],"solving":[11],"tasks":[12,18,126,146],"with":[13,102,152],"sparse":[14,153],"rewards.":[15,154],"However,":[16],"the":[17,29,43,46,58,63,67,72,74,80,103,109,117,121,132],"real-world":[20],"scenarios":[21],"can":[22,99],"often":[23],"have":[24],"varied":[25],"initial":[26],"conditions":[27],"from":[28,53],"demonstration,":[30],"which":[31],"would":[32],"require":[33],"additional":[34,129],"prior":[35,68,111,133],"behaviours.":[36,134],"For":[37],"example,":[38],"consider":[39],"we":[40,88],"given":[42],"demonstration":[44,122,130],"task":[47,151],"of":[48,70,131,137],"picking":[49],"up":[50],"an":[51,54,90],"object":[52],"open":[55],"drawer,":[56,73],"but":[57],"drawer":[59],"is":[60,76],"closed":[61],"training.":[64],"Without":[65],"acquiring":[66],"behaviours":[69,112,119],"opening":[71],"robot":[75],"unlikely":[77],"to":[78,105,116,123],"solve":[79,124],"task.":[81],"To":[82],"address":[83],"this,":[84],"this":[86],"paper":[87],"propose":[89],"Intrinsic":[91],"Reward":[92],"Driven":[93],"Example-based":[94],"Control":[95],"(IRDEC).":[96],"Our":[97],"method":[98,139],"endow":[100],"agents":[101],"ability":[104],"explore":[106],"and":[107,113,147],"acquire":[108],"required":[110],"then":[114],"connect":[115],"task-specific":[118],"sparse-reward":[125],"without":[127],"requiring":[128],"The":[135],"performance":[136],"our":[138],"outperforms":[140],"other":[141],"baselines":[142],"on":[143],"three":[144],"navigation":[145],"one":[148],"robotic":[149],"manipulation":[150],"Codes":[155],"available":[157],"at":[158],"https://github.com/Ricky-Zhu/IRDEC.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}