{"id":"https://openalex.org/W4312539161","doi":"https://doi.org/10.1109/iros47612.2022.9982282","title":"Keeping Humans in the Loop: Teaching via Feedback in Continuous Action Space Environments","display_name":"Keeping Humans in the Loop: Teaching via Feedback in Continuous Action Space Environments","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312539161","doi":"https://doi.org/10.1109/iros47612.2022.9982282"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9982282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982282","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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 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/A5070000164","display_name":"Isaac Sheidlower","orcid":"https://orcid.org/0009-0004-4487-8357"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac Sheidlower","raw_affiliation_strings":["Tufts University School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University School of Engineering","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103116723","display_name":"Allison Moore","orcid":"https://orcid.org/0000-0002-5506-4584"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allison Moore","raw_affiliation_strings":["Tufts University School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University School of Engineering","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077011363","display_name":"Elaine Schaertl Short","orcid":"https://orcid.org/0000-0002-4789-9979"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elaine Short","raw_affiliation_strings":["Tufts University School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University School of Engineering","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":null,"apc_paid":null,"fwci":1.3495,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.837607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"863","last_page":"870"},"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":0.9945999979972839,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8162050247192383},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7448010444641113},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6719027161598206},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6283501386642456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6009876728057861},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5428637266159058},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.532193660736084},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5102279186248779},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5033881068229675},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4786299765110016},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4680953323841095},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4218495190143585},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38068294525146484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0843154788017273}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8162050247192383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448010444641113},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6719027161598206},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6283501386642456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6009876728057861},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5428637266159058},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.532193660736084},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5102279186248779},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5033881068229675},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4786299765110016},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4680953323841095},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4218495190143585},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38068294525146484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0843154788017273},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9982282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982282","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W122021961","https://openalex.org/W1777239053","https://openalex.org/W1979308911","https://openalex.org/W2098441518","https://openalex.org/W2108598243","https://openalex.org/W2145339207","https://openalex.org/W2156869222","https://openalex.org/W2291647668","https://openalex.org/W2409653330","https://openalex.org/W2573393487","https://openalex.org/W2736601468","https://openalex.org/W2751516180","https://openalex.org/W2774894600","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2799745602","https://openalex.org/W2898227854","https://openalex.org/W2904246096","https://openalex.org/W2904453761","https://openalex.org/W2913350117","https://openalex.org/W2947150733","https://openalex.org/W2963489214","https://openalex.org/W2979417040","https://openalex.org/W3006334608","https://openalex.org/W3008535267","https://openalex.org/W3039116038","https://openalex.org/W3094236223","https://openalex.org/W3096621767","https://openalex.org/W3101103779","https://openalex.org/W3103105396","https://openalex.org/W3115850754","https://openalex.org/W3131966994","https://openalex.org/W4287113927","https://openalex.org/W4288083537","https://openalex.org/W4288593469","https://openalex.org/W4300110528","https://openalex.org/W4300799055","https://openalex.org/W4321392130","https://openalex.org/W6638088447","https://openalex.org/W6674812091","https://openalex.org/W6732417791","https://openalex.org/W6739585900","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6755473067","https://openalex.org/W6757469721","https://openalex.org/W6757592117","https://openalex.org/W6758427599","https://openalex.org/W6759301632","https://openalex.org/W6763704811","https://openalex.org/W6891918056"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2914522629","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Interactive":[0,65,171],"Reinforcement":[1,13,66],"Learning":[2,14],"(IntRL)":[3],"allows":[4,115],"human":[5,156],"teachers":[6],"to":[7,23,38,57,82,119],"accelerate":[8],"the":[9,45,69,95,98,107,167],"learning":[10,67],"process":[11],"of":[12,78],"(RL)":[15],"robots.":[16],"However,":[17],"IntRL":[18,73],"has":[19],"largely":[20],"been":[21],"limited":[22],"tasks":[24,47,140],"with":[25,141],"discrete-action":[26],"spaces":[27],"in":[28,87,136,154,170],"which":[29],"actions":[30],"are":[31],"relatively":[32,122],"slow.":[33],"This":[34,114],"limits":[35],"IntRL's":[36],"application":[37],"more":[39],"complicated":[40],"and":[41,97,143,163],"challenging":[42],"robotic":[43],"tasks,":[44],"very":[46],"that":[48,75,104],"modern":[49],"RL":[50,85],"is":[51,76],"particularly":[52],"well-suited":[53],"for.":[54],"We":[55,132],"seek":[56],"bridge":[58],"this":[59],"gap":[60],"by":[61],"presenting":[62],"Continuous":[63],"Action-space":[64],"(CAIR):":[68],"first":[70],"continuous":[71],"action-space":[72],"algorithm":[74],"capable":[77],"using":[79],"teacher":[80,99,130],"feedback":[81],"out-perform":[83],"state-of-the-art":[84,169],"algorithms":[86],"those":[88],"tasks.":[89],"CAIR":[90,117,165],"combines":[91],"policies":[92,109],"learned":[93],"from":[94],"environment":[96],"into":[100],"a":[101,116,121,155],"single":[102],"policy":[103,124],"proportionally":[105],"weights":[106],"two":[108,137],"based":[110],"on":[111],"their":[112],"agreement.":[113],"agent":[118],"learn":[120],"stable":[123],"despite":[125],"potentially":[126],"noisy":[127],"or":[128],"coarse":[129],"feedback.":[131],"validate":[133,151],"our":[134,152],"approach":[135,153],"simulated":[138],"robotics":[139],"easy-to-design":[142],"-":[144],"understand":[145],"heuristic":[146],"oracle":[147],"teachers.":[148],"Furthermore,":[149],"we":[150],"subjects":[157],"study":[158],"through":[159],"Amazon":[160],"Mechanical":[161],"Turk":[162],"show":[164],"out-performs":[166],"prior":[168],"RL.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}