{"id":"https://openalex.org/W4383755721","doi":"https://doi.org/10.1007/s10514-023-10120-w","title":"Learning rewards from exploratory demonstrations using probabilistic temporal ranking","display_name":"Learning rewards from exploratory demonstrations using probabilistic temporal ranking","publication_year":2023,"publication_date":"2023-07-10","ids":{"openalex":"https://openalex.org/W4383755721","doi":"https://doi.org/10.1007/s10514-023-10120-w"},"language":"en","primary_location":{"id":"doi:10.1007/s10514-023-10120-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-023-10120-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-023-10120-w.pdf","source":{"id":"https://openalex.org/S144091109","display_name":"Autonomous Robots","issn_l":"0929-5593","issn":["0929-5593","1573-7527"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Robots","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10514-023-10120-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059032849","display_name":"Michael Burke","orcid":"https://orcid.org/0000-0001-7426-1498"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Michael Burke","raw_affiliation_strings":["Electrical and Computer Systems Engineering, Monash University, Clayton, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7426-1498","affiliations":[{"raw_affiliation_string":"Electrical and Computer Systems Engineering, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030010125","display_name":"Katie Lu","orcid":"https://orcid.org/0009-0000-8588-2505"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Katie Lu","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070418190","display_name":"Daniel Angelov","orcid":"https://orcid.org/0000-0001-7292-5182"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Angelov","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076899063","display_name":"Art\u016bras Strai\u017eys","orcid":"https://orcid.org/0000-0001-7569-2265"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Art\u016bras Strai\u017eys","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618980","display_name":"Craig Innes","orcid":"https://orcid.org/0000-0002-6329-4136"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Innes","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086009008","display_name":"Kartic Subr","orcid":"https://orcid.org/0000-0002-7302-4383"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kartic Subr","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071122608","display_name":"Subramanian Ramamoorthy","orcid":"https://orcid.org/0000-0002-6300-5103"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Subramanian Ramamoorthy","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059032849"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":{"value":2590,"currency":"EUR","value_usd":3390},"apc_paid":{"value":2590,"currency":"EUR","value_usd":3390},"fwci":10.923,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.97700725,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"47","issue":"6","first_page":"733","last_page":"751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10531","display_name":"Advanced Vision and Imaging","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8393580913543701},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6796400547027588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6597571969032288},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6117286086082458},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.579852819442749},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5365422368049622},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5131197571754456},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5000743865966797},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4964144825935364},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4790195822715759},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.45490819215774536},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3365820646286011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8393580913543701},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6796400547027588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6597571969032288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6117286086082458},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.579852819442749},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5365422368049622},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5131197571754456},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5000743865966797},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4964144825935364},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4790195822715759},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.45490819215774536},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3365820646286011},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10514-023-10120-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-023-10120-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-023-10120-w.pdf","source":{"id":"https://openalex.org/S144091109","display_name":"Autonomous Robots","issn_l":"0929-5593","issn":["0929-5593","1573-7527"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Robots","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/e68fdb95-238a-439b-b954-7e6534de54ad","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/e68fdb95-238a-439b-b954-7e6534de54ad","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Burke, M, Lu, K, Angelov, D, Straizys, A, Innes, C, Subr, K & Ramamoorthy, S 2023, 'Learning rewards from exploratory demonstrations using probabilistic temporal ranking', Autonomous Robots, vol. 47, no. 6, pp. 733-751. https://doi.org/10.1007/s10514-023-10120-w","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/e68fdb95-238a-439b-b954-7e6534de54ad","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/e68fdb95-238a-439b-b954-7e6534de54ad","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.1007/s10514-023-10120-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-023-10120-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-023-10120-w.pdf","source":{"id":"https://openalex.org/S144091109","display_name":"Autonomous Robots","issn_l":"0929-5593","issn":["0929-5593","1573-7527"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Robots","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G5604127548","display_name":null,"funder_award_id":"EP/R019606/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320313467","display_name":"Alan Turing Institute","ror":"https://ror.org/035dkdb55"},{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4383755721.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W181871703","https://openalex.org/W1544131626","https://openalex.org/W1583092270","https://openalex.org/W1965520710","https://openalex.org/W1979728958","https://openalex.org/W1982413096","https://openalex.org/W1990552485","https://openalex.org/W1999874108","https://openalex.org/W2018020586","https://openalex.org/W2079776780","https://openalex.org/W2083327122","https://openalex.org/W2091568354","https://openalex.org/W2096649264","https://openalex.org/W2098774185","https://openalex.org/W2102031973","https://openalex.org/W2117675763","https://openalex.org/W2120415087","https://openalex.org/W2131175218","https://openalex.org/W2133068870","https://openalex.org/W2135624041","https://openalex.org/W2153975459","https://openalex.org/W2156163138","https://openalex.org/W2169003314","https://openalex.org/W2188721763","https://openalex.org/W2217402295","https://openalex.org/W2260756217","https://openalex.org/W2290226688","https://openalex.org/W2395738761","https://openalex.org/W2528041826","https://openalex.org/W2529184366","https://openalex.org/W2566638765","https://openalex.org/W2566837261","https://openalex.org/W2734346390","https://openalex.org/W2738812390","https://openalex.org/W2766610320","https://openalex.org/W2769112066","https://openalex.org/W2785324569","https://openalex.org/W2939047085","https://openalex.org/W2963945780","https://openalex.org/W2980192220","https://openalex.org/W2988072049","https://openalex.org/W3006033038","https://openalex.org/W3039563104","https://openalex.org/W3091627088","https://openalex.org/W3216772467","https://openalex.org/W4211049957","https://openalex.org/W4252841025","https://openalex.org/W6637650041","https://openalex.org/W6675104829","https://openalex.org/W6696273291","https://openalex.org/W6718092244","https://openalex.org/W6759312711"],"related_works":["https://openalex.org/W2372267530","https://openalex.org/W2969189870","https://openalex.org/W3015855446","https://openalex.org/W4303857162","https://openalex.org/W2965643117","https://openalex.org/W4288266653","https://openalex.org/W2407375987","https://openalex.org/W2505726097","https://openalex.org/W2950975704","https://openalex.org/W3049691116"],"abstract_inverted_index":{"Abstract":[0],"Informative":[1],"path-planning":[2,65],"is":[3,27,41],"a":[4,20,44,57,62,130,152,179,195],"well":[5],"established":[6],"approach":[7,95,162],"to":[8,48,75,81,96,126,137,171],"visual-servoing":[9],"and":[10,43,133,143,163],"active":[11],"viewpoint":[12],"selection":[13],"in":[14,61,112,186],"robotics,":[15],"but":[16],"typically":[17],"assumes":[18],"that":[19,147,165],"suitable":[21],"cost":[22],"function":[23,46],"or":[24],"goal":[25,37],"state":[26],"known.":[28],"This":[29],"work":[30],"considers":[31],"the":[32,36,39,82,86,99],"inverse":[33],"problem,":[34],"where":[35,103],"of":[38,78,85,101,119,182,192,198],"task":[40],"unknown,":[42],"reward":[45,70,145,173],"needs":[47],"be":[49,127],"inferred":[50],"from":[51,184,201],"exploratory":[52,83,106],"example":[53],"demonstrations":[54,107],"provided":[55],"by":[56],"demonstrator,":[58],"for":[59,175],"use":[60,134],"downstream":[63],"informative":[64],"policy.":[66],"Unfortunately,":[67],"many":[68],"existing":[69,169],"inference":[71,174],"strategies":[72],"are":[73,122],"unsuited":[74],"this":[76,89,135,158],"class":[77,100],"problems,":[79],"due":[80],"nature":[84],"demonstrations.":[87],"In":[88],"paper,":[90],"we":[91],"propose":[92],"an":[93],"alternative":[94],"cope":[97],"with":[98,129],"problems":[102],"these":[104,149],"sub-optimal,":[105],"occur.":[108],"We":[109,156],"hypothesise":[110],"that,":[111],"tasks":[113],"which":[114],"require":[115],"discovery,":[116],"successive":[117],"states":[118],"any":[120],"demonstration":[121,185,202],"progressively":[123],"more":[124],"likely":[125],"associated":[128],"higher":[131],"reward,":[132],"hypothesis":[136],"generate":[138],"time-based":[139],"binary":[140],"comparison":[141],"outcomes":[142],"infer":[144],"functions":[146],"support":[148],"ranks,":[150],"under":[151],"probabilistic":[153,159],"generative":[154],"model.":[155],"formalise":[157],"temporal":[160],"ranking":[161],"show":[164],"it":[166],"improves":[167],"upon":[168],"approaches":[170],"perform":[172],"autonomous":[176],"ultrasound":[177],"scanning,":[178],"novel":[180],"application":[181],"learning":[183,200],"medical":[187],"imaging":[188],"while":[189],"also":[190],"being":[191],"value":[193],"across":[194],"broad":[196],"range":[197],"goal-oriented":[199],"tasks.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
