{"id":"https://openalex.org/W4389667649","doi":"https://doi.org/10.1109/iros55552.2023.10341990","title":"Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores","display_name":"Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667649","doi":"https://doi.org/10.1109/iros55552.2023.10341990"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341990","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341990","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/A5035078709","display_name":"Shukai Liu","orcid":"https://orcid.org/0000-0001-7369-2958"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shukai Liu","raw_affiliation_strings":["University of Bristol,Department of Engineering Mathematics,UK","Department of Engineering Mathematics, University of Bristol, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol,Department of Engineering Mathematics,UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Department of Engineering Mathematics, University of Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103089859","display_name":"Chenming Wu","orcid":"https://orcid.org/0000-0001-8012-1547"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenming Wu","raw_affiliation_strings":["Baidu Research,RAL","RAL, Baidu Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research,RAL","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"RAL, Baidu Research","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414383","display_name":"Ying Li","orcid":"https://orcid.org/0000-0003-0608-9619"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["School of Mechanical Engineering, Beijing Institute of Technology,Beijing,China","School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101843626","display_name":"Liangjun Zhang","orcid":"https://orcid.org/0000-0001-5737-2540"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangjun Zhang","raw_affiliation_strings":["Baidu Research,RAL","RAL, Baidu Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research,RAL","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"RAL, Baidu Research","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49222898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7561","last_page":"7567"},"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":0.9948999881744385,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9861000180244446,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.8376680612564087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7995021343231201},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7987070083618164},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6500386595726013},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6258267760276794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.610988974571228},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.5316351652145386},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5019299983978271},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4727547764778137},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"Interactive Learning","score":0.4193841218948364},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33277037739753723},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.0884709358215332},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08017027378082275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0728064477443695}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.8376680612564087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995021343231201},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7987070083618164},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6500386595726013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6258267760276794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.610988974571228},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.5316351652145386},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5019299983978271},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4727547764778137},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.4193841218948364},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33277037739753723},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0884709358215332},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08017027378082275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0728064477443695},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341990","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341990","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":55,"referenced_works":["https://openalex.org/W1929981607","https://openalex.org/W1999874108","https://openalex.org/W2098441518","https://openalex.org/W2108862644","https://openalex.org/W2135043890","https://openalex.org/W2156869222","https://openalex.org/W2158782408","https://openalex.org/W2183341477","https://openalex.org/W2201581102","https://openalex.org/W2414920489","https://openalex.org/W2486334580","https://openalex.org/W2502094132","https://openalex.org/W2567252694","https://openalex.org/W2612346912","https://openalex.org/W2741122588","https://openalex.org/W2763110165","https://openalex.org/W2914931737","https://openalex.org/W3000002597","https://openalex.org/W3007769740","https://openalex.org/W3093784762","https://openalex.org/W3111294788","https://openalex.org/W3122928565","https://openalex.org/W3138984732","https://openalex.org/W3202542428","https://openalex.org/W3212723749","https://openalex.org/W4212901515","https://openalex.org/W4214717370","https://openalex.org/W4221163700","https://openalex.org/W4226146935","https://openalex.org/W4281800227","https://openalex.org/W4287122174","https://openalex.org/W4312480554","https://openalex.org/W4321392130","https://openalex.org/W6604828220","https://openalex.org/W6635261211","https://openalex.org/W6640443443","https://openalex.org/W6674812091","https://openalex.org/W6674884181","https://openalex.org/W6687681856","https://openalex.org/W6696265566","https://openalex.org/W6696380822","https://openalex.org/W6732417791","https://openalex.org/W6739585900","https://openalex.org/W6742461812","https://openalex.org/W6743368274","https://openalex.org/W6747473740","https://openalex.org/W6761908843","https://openalex.org/W6769174716","https://openalex.org/W6769596995","https://openalex.org/W6785034342","https://openalex.org/W6796168157","https://openalex.org/W6799431981","https://openalex.org/W6801328502","https://openalex.org/W6810044100","https://openalex.org/W6838843634"],"related_works":["https://openalex.org/W1515481220","https://openalex.org/W2060303324","https://openalex.org/W4206238124","https://openalex.org/W4324116389","https://openalex.org/W3126212998","https://openalex.org/W2516425091","https://openalex.org/W3105737538","https://openalex.org/W2403029370","https://openalex.org/W4200207182","https://openalex.org/W2785054398"],"abstract_inverted_index":{"Interactive":[0],"reinforcement":[1,51],"learning":[2,7,107,112,147,158],"has":[3],"shown":[4],"promise":[5],"in":[6,86],"complex":[8],"robotic":[9,128],"tasks.":[10,132],"However,":[11],"the":[12,19,46,75,100,111,137],"process":[13],"can":[14,59,140],"be":[15,115],"human-intensive":[16],"due":[17],"to":[18,44,72,81,114,117,155],"requirement":[20],"of":[21,25,41,49,78],"a":[22,31,70,83,87],"large":[23],"amount":[24],"interactive":[26,50],"feedback.":[27],"This":[28,109],"paper":[29],"presents":[30],"new":[32],"method":[33,126,139],"that":[34,57,136],"uses":[35],"scores":[36,58,94,149],"provided":[37],"by":[38,96,145],"humans":[39,97],"instead":[40],"pairwise":[42,65,156],"preferences":[43],"improve":[45],"feedback":[47,153],"efficiency":[48],"learning.":[52],"Our":[53],"key":[54],"insight":[55],"is":[56],"yield":[60],"significantly":[61],"more":[62],"data":[63],"than":[64],"preferences.":[66],"Specifically,":[67],"we":[68,103],"require":[69],"teacher":[71],"interactively":[73],"score":[74],"full":[76],"trajectories":[77],"an":[79,105],"agent":[80],"train":[82],"behavioral":[84],"policy":[85],"sparse":[88],"reward":[89],"environment.":[90],"To":[91],"avoid":[92],"unstable":[93],"given":[95],"negatively":[98],"impacting":[99],"training":[101],"process,":[102],"propose":[104],"adaptive":[106,146],"scheme.":[108],"enables":[110],"paradigm":[113],"insensitive":[116],"imperfect":[118],"or":[119],"unreliable":[120],"scores.":[121],"We":[122],"extensively":[123],"evaluate":[124],"our":[125],"for":[127],"locomotion":[129],"and":[130],"manipulation":[131],"The":[133,160],"results":[134],"show":[135],"proposed":[138],"efficiently":[141],"learn":[142],"near-optimal":[143],"policies":[144],"from":[148],"while":[150],"requiring":[151],"less":[152],"compared":[154],"preference":[157],"methods.":[159],"source":[161],"codes":[162],"are":[163],"publicly":[164],"available":[165],"at":[166],"https://github.com/SSKKai/Interactive-Scoring-IRL.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}