{"id":"https://openalex.org/W4389665396","doi":"https://doi.org/10.1109/iros55552.2023.10342180","title":"Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot","display_name":"Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665396","doi":"https://doi.org/10.1109/iros55552.2023.10342180"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342180","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/A5100620477","display_name":"Tao Huang","orcid":"https://orcid.org/0000-0002-0879-1850"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Huang","raw_affiliation_strings":["The Chinese University of Hong Kong,The Department of Computer Science and Engineering","The Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437926","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-6850-1723"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,The Department of Computer Science and Engineering","The Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391883","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-1430-1360"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Wei","raw_affiliation_strings":["The Chinese University of Hong Kong,The Department of Computer Science and Engineering","The Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448294","display_name":"Jianan Li","orcid":"https://orcid.org/0000-0002-8676-927X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianan Li","raw_affiliation_strings":["The Chinese University of Hong Kong,The Department of Computer Science and Engineering","The Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040473879","display_name":"Yonghao Long","orcid":"https://orcid.org/0000-0003-4474-7854"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghao Long","raw_affiliation_strings":["The Chinese University of Hong Kong,The Department of Computer Science and Engineering","The Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090516040","display_name":"Qi Dou","orcid":"https://orcid.org/0000-0002-3416-9950"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Dou","raw_affiliation_strings":["The Chinese University of Hong Kong,The Department of Computer Science and Engineering","The Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100620477"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.3092,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81643708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9846000075340271,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9520999789237976,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chaining","display_name":"Chaining","score":0.9368656873703003},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8655165433883667},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7624567151069641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7160857915878296},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6731218099594116},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.6599751114845276},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6260770559310913},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5186564326286316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4996790885925293},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4934900999069214},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.48952898383140564},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4454362392425537},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.441676527261734},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3379405736923218},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31044524908065796},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.168156236410141},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13646718859672546},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11494606733322144},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11244770884513855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07740503549575806}],"concepts":[{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.9368656873703003},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8655165433883667},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7624567151069641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160857915878296},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6731218099594116},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.6599751114845276},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6260770559310913},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5186564326286316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4996790885925293},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4934900999069214},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.48952898383140564},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4454362392425537},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.441676527261734},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3379405736923218},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31044524908065796},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.168156236410141},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13646718859672546},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11494606733322144},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11244770884513855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07740503549575806},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"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/iros55552.2023.10342180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342180","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1963873191","https://openalex.org/W2108535023","https://openalex.org/W2593390416","https://openalex.org/W2735048916","https://openalex.org/W2736750746","https://openalex.org/W2902791462","https://openalex.org/W2911024029","https://openalex.org/W2963099939","https://openalex.org/W2970377754","https://openalex.org/W2973815009","https://openalex.org/W3004503628","https://openalex.org/W3016521739","https://openalex.org/W3094103188","https://openalex.org/W3103266692","https://openalex.org/W3126321819","https://openalex.org/W3130448017","https://openalex.org/W3133389372","https://openalex.org/W3190864623","https://openalex.org/W3196343109","https://openalex.org/W3196757288","https://openalex.org/W3198013102","https://openalex.org/W3200480656","https://openalex.org/W4200341796","https://openalex.org/W4200633290","https://openalex.org/W4224938351","https://openalex.org/W4226137952","https://openalex.org/W4287756699","https://openalex.org/W4288021424","https://openalex.org/W4383097529","https://openalex.org/W6616173779","https://openalex.org/W6631190155","https://openalex.org/W6676557315","https://openalex.org/W6730038592","https://openalex.org/W6745983339","https://openalex.org/W6747473740","https://openalex.org/W6748523217","https://openalex.org/W6751540476","https://openalex.org/W6758134627","https://openalex.org/W6765008394","https://openalex.org/W6771398375","https://openalex.org/W6772008794","https://openalex.org/W6779656125","https://openalex.org/W6802988130","https://openalex.org/W6804064799"],"related_works":["https://openalex.org/W2906267174","https://openalex.org/W134501823","https://openalex.org/W2615656344","https://openalex.org/W2809608782","https://openalex.org/W2013239059","https://openalex.org/W2295626654","https://openalex.org/W2333245620","https://openalex.org/W4286622840","https://openalex.org/W2536121351","https://openalex.org/W1889576908"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,120],"is":[2,42,70,130,136,176,235],"still":[3],"struggling":[4],"with":[5,187],"solving":[6],"long-horizon":[7,40,62,123],"surgical":[8,73,124,216,223],"robot":[9,74,125,217],"tasks":[10,218],"which":[11,38,133],"involve":[12],"multiple":[13,45],"steps":[14],"over":[15],"an":[16],"extended":[17],"duration":[18],"of":[19,91,161,210],"time":[20],"due":[21],"to":[22,30,58,131,178,182,199],"the":[23,39,49,60,92,97,141,157,162,185,188,204,208],"policy":[24,100,175],"exploration":[25,50],"challenge.":[26],"Recent":[27],"methods":[28],"try":[29],"tackle":[31],"this":[32,109,147,170],"problem":[33],"by":[34],"skill":[35,114],"chaining,":[36],"in":[37,104],"task":[41,164,228],"decomposed":[43],"into":[44],"subtasks":[46],"for":[47,72,82,122,138,202],"easing":[48],"burden":[51],"and":[52,102,231],"subtask":[53,68,94,99,143,180],"policies":[54,69,181,195],"are":[55,79,196],"temporally":[56],"connected":[57,201],"complete":[59],"whole":[61],"task.":[63,205],"However,":[64],"smoothly":[65],"connecting":[66,83],"all":[67,77,140,193],"difficult":[71],"scenarios.":[75],"Not":[76],"states":[78],"equally":[80],"suitable":[81,137],"two":[84],"adjacent":[85],"subtasks.":[86],"An":[87],"undesired":[88],"terminate":[89,183],"state":[90,135,152,186],"previous":[93],"would":[95],"make":[96],"current":[98],"unstable":[101],"result":[103],"a":[105,117,151,166,173,221],"failed":[106],"execution.":[107],"In":[108],"work,":[110],"we":[111,149],"introduce":[112,150],"value-informed":[113],"chaining":[115,174],"(ViSkill),":[116],"novel":[118],"reinforcement":[119],"framework":[121],"tasks.":[126],"The":[127],"core":[128],"idea":[129],"distinguish":[132],"terminal":[134],"starting":[139],"following":[142],"policies.":[144],"To":[145],"achieve":[146],"target,":[148],"value":[153,171,190],"function":[154],"that":[155,192],"estimates":[156],"expected":[158],"success":[159,229],"probability":[160],"entire":[163],"given":[165],"state.":[167],"Based":[168],"on":[169,213],"function,":[172],"learned":[177],"instruct":[179],"at":[184,237],"highest":[189],"so":[191],"subsequent":[194],"more":[197],"likely":[198],"be":[200],"accomplishing":[203],"We":[206],"demonstrate":[207],"effectiveness":[209],"our":[211],"method":[212],"three":[214],"complex":[215],"from":[219],"SurRoL,":[220],"comprehensive":[222],"simulation":[224],"platform,":[225],"achieving":[226],"high":[227],"rates":[230],"execution":[232],"efficiency.":[233],"Code":[234],"available":[236],"https:":[238],"/":[239],"/github.":[240],"com/med-air/ViSkill.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}