{"id":"https://openalex.org/W4389352652","doi":"https://doi.org/10.1109/lra.2023.3339400","title":"Sketch RL: Interactive Sketch Generation for Long-Horizon Tasks via Vision-Based Skill Predictor","display_name":"Sketch RL: Interactive Sketch Generation for Long-Horizon Tasks via Vision-Based Skill Predictor","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4389352652","doi":"https://doi.org/10.1109/lra.2023.3339400"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3339400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3339400","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5059283626","display_name":"Zhenyang Lin","orcid":"https://orcid.org/0000-0002-1361-4824"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyang Lin","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041934391","display_name":"Yurou Chen","orcid":"https://orcid.org/0000-0002-0022-7219"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yurou Chen","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100434504","display_name":"Zhiyong Liu","orcid":"https://orcid.org/0000-0003-2148-1846"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Liu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059283626"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210100255","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.8757,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79544993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"9","issue":"1","first_page":"867","last_page":"874"},"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":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/sketch","display_name":"Sketch","score":0.8403915166854858},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8054287433624268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7917423248291016},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6606767177581787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6550992131233215},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.6055576205253601},{"id":"https://openalex.org/keywords/sketch-recognition","display_name":"Sketch recognition","score":0.5180125832557678},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49546492099761963},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45232754945755005},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43289855122566223},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34795352816581726}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8403915166854858},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8054287433624268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917423248291016},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6606767177581787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6550992131233215},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.6055576205253601},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.5180125832557678},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49546492099761963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45232754945755005},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43289855122566223},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34795352816581726},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.0},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3339400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3339400","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2066379939","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2209913494","https://openalex.org/W2531264786","https://openalex.org/W2788862220","https://openalex.org/W2897239789","https://openalex.org/W2964227312","https://openalex.org/W2966271811","https://openalex.org/W2975504670","https://openalex.org/W2991489433","https://openalex.org/W3035850588","https://openalex.org/W3048659003","https://openalex.org/W3088304681","https://openalex.org/W3090054427","https://openalex.org/W3204657926","https://openalex.org/W4225873172","https://openalex.org/W4287756699","https://openalex.org/W6682849425","https://openalex.org/W6717697761","https://openalex.org/W6730038592","https://openalex.org/W6734215269","https://openalex.org/W6738261575","https://openalex.org/W6747473740","https://openalex.org/W6747943641","https://openalex.org/W6748566876","https://openalex.org/W6748603076","https://openalex.org/W6752089545","https://openalex.org/W6752165109","https://openalex.org/W6756675569","https://openalex.org/W6760439459","https://openalex.org/W6770704954","https://openalex.org/W6771398375","https://openalex.org/W6779099061","https://openalex.org/W6779656125","https://openalex.org/W6779830607","https://openalex.org/W6781678525","https://openalex.org/W6782766965","https://openalex.org/W6785876034","https://openalex.org/W6800564222","https://openalex.org/W6810080435","https://openalex.org/W6846049332"],"related_works":["https://openalex.org/W2294900353","https://openalex.org/W2411243951","https://openalex.org/W2151314278","https://openalex.org/W1971224820","https://openalex.org/W13629514","https://openalex.org/W2963977451","https://openalex.org/W2098836165","https://openalex.org/W1976890290","https://openalex.org/W1573697454","https://openalex.org/W2966897482"],"abstract_inverted_index":{"For":[0],"autonomous":[1],"robots,":[2],"it":[3,109],"is":[4,160],"desirable":[5],"to":[6,46,113,119,127,138,164],"learn":[7],"coordination":[8],"of":[9,36,162],"primitive":[10,37],"skills":[11,38,61],"that":[12,30,95,150],"can":[13,43],"effectively":[14],"solve":[15],"long-horizon":[16,86],"tasks":[17,33,148,166],"and":[18,107,124,159,170],"perform":[19,47],"novel":[20],"ones.":[21],"Recent":[22],"advances":[23],"in":[24,50,59,62],"hierarchical":[25,93],"policy":[26],"learning":[27,98,101],"have":[28],"shown":[29],"decomposing":[31],"complex":[32],"into":[34],"sequences":[35],"which":[39],"are":[40,72],"called":[41],"sketches":[42,71,169],"enable":[44],"robots":[45],"directed":[48],"exploration":[49,83],"challenging":[51,146],"manipulation":[52,147],"tasks.":[53],"However,":[54],"they":[55],"usually":[56],"fall":[57],"short":[58],"sequencing":[60],"a":[63,92,133],"new":[64,128,165],"task":[65,70,105],"without":[66],"retraining":[67],"as":[68,110],"the":[69,104,111],"almost":[73],"hard-coded":[74],"or":[75],"learned":[76],"by":[77],"deep":[78],"reinforcement":[79,100],"learning.":[80,117],"To":[81],"improve":[82],"efficiency":[84],"for":[85,121],"tasks,":[87,129],"we":[88],"propose":[89],"Sketch":[90,151],"RL,":[91],"framework":[94],"combines":[96],"supervised":[97],"with":[99,167],"interactively":[102],"generates":[103],"sketch,":[106],"utilizes":[108],"curriculum":[112],"guide":[114],"low-level":[115],"skill":[116],"Furthermore,":[118],"allow":[120],"multitask":[122],"decomposition":[123],"generalizing":[125],"few-shot":[126],"our":[130],"method":[131],"exploits":[132],"Vision-based":[134],"Skill":[135],"Predictor":[136],"(VSP)":[137],"capture":[139],"shared":[140],"subtask":[141],"structure.":[142],"Extensive":[143],"experiments":[144],"on":[145],"demonstrate":[149],"RL":[152],"substantially":[153],"outperforms":[154],"other":[155],"prior":[156],"baseline":[157],"methods":[158],"capable":[161],"adapting":[163],"different":[168],"real-world":[171],"settings.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}