{"id":"https://openalex.org/W4412444550","doi":"https://doi.org/10.1109/access.2025.3588936","title":"TEMPO: Timestep Explanations for Modeling Preferences in Online Preference-Based RL","display_name":"TEMPO: Timestep Explanations for Modeling Preferences in Online Preference-Based RL","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412444550","doi":"https://doi.org/10.1109/access.2025.3588936"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3588936","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3588936","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3588936","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118995107","display_name":"Jakob Karlaus","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jakob Karlaus","raw_affiliation_strings":["Institute of Artificial Intelligence, Ulm University, Ulm, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078096723","display_name":"Friedhelm Schwenker","orcid":"https://orcid.org/0000-0001-5118-0812"},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]},{"id":"https://openalex.org/I4210163522","display_name":"Technische Hochschule Ulm","ror":"https://ror.org/05e5kd476","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210163522"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Friedhelm Schwenker","raw_affiliation_strings":["Institute of Neuroinformatics, Ulm University, Ulm, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Neuroinformatics, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391","https://openalex.org/I4210163522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5118995107"],"corresponding_institution_ids":["https://openalex.org/I196349391"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24739926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"125759","last_page":"125771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9686999917030334,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9686999917030334,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9211000204086304,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9135000109672546,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7297141551971436},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.689174473285675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3776789605617523},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17865365743637085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12720352411270142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297141551971436},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.689174473285675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3776789605617523},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17865365743637085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12720352411270142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3588936","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3588936","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:37d64b8a2727437691bb6aabacb7c936","is_oa":true,"landing_page_url":"https://doaj.org/article/37d64b8a2727437691bb6aabacb7c936","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 125759-125771 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3588936","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3588936","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1501005121","https://openalex.org/W2110064869","https://openalex.org/W2154023516","https://openalex.org/W2156300785","https://openalex.org/W2516809705","https://openalex.org/W2763110165","https://openalex.org/W2963798744","https://openalex.org/W3171209108","https://openalex.org/W3192495122","https://openalex.org/W4312777094","https://openalex.org/W4382239386","https://openalex.org/W4385767460","https://openalex.org/W4387185475","https://openalex.org/W4401417401","https://openalex.org/W4405786804","https://openalex.org/W6685133223","https://openalex.org/W6694177581","https://openalex.org/W6734194636","https://openalex.org/W6739575509","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6744991969","https://openalex.org/W6747473740","https://openalex.org/W6747820993","https://openalex.org/W6766375498","https://openalex.org/W6796168157","https://openalex.org/W6797119598","https://openalex.org/W6799431981","https://openalex.org/W6800570120","https://openalex.org/W6801727026","https://openalex.org/W6803321137","https://openalex.org/W6810044100","https://openalex.org/W6838843634","https://openalex.org/W6853227753","https://openalex.org/W6855173278","https://openalex.org/W6856361044","https://openalex.org/W6860276258"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Human-in-the-loop":[0],"reinforcement":[1],"learning":[2,55,120,138],"enables":[3],"non-expert":[4],"users":[5],"to":[6,22,60,122],"train":[7],"agents":[8],"through":[9],"interactive":[10],"feedback.":[11],"While":[12],"preference-based":[13,54,124],"methods":[14,125],"(PbRL)":[15],"have":[16],"gained":[17],"popularity":[18],"by":[19,31],"allowing":[20],"humans":[21,37,59],"express":[23],"preferences":[24],"between":[25],"trajectory":[26,42],"pairs,":[27],"they":[28,43],"are":[29],"limited":[30],"their":[32,65,72],"narrow":[33],"feedback":[34,134],"interface":[35],"-":[36],"can":[38],"only":[39],"indicate":[40],"which":[41,68],"prefer":[44],"but":[45],"not":[46],"why.":[47],"This":[48],"work":[49],"introduces":[50],"a":[51,79,87,148],"more":[52,141,155],"expressive":[53],"framework":[56],"that":[57,82,116,145],"allows":[58],"provide":[61],"step-level":[62],"explanations":[63,85],"alongside":[64],"preferences,":[66],"indicating":[67],"specific":[69],"timesteps":[70],"influenced":[71],"decisions.":[73],"Our":[74],"key":[75],"technical":[76],"innovation":[77],"is":[78,147],"training":[80],"approach":[81,118],"incorporates":[83],"these":[84],"using":[86,107],"novel":[88],"loss":[89],"function":[90],"combining":[91],"reward":[92],"learning,":[93],"saliency-based":[94],"explanations,":[95],"and":[96,111,140],"structural":[97],"regularization.We":[98],"evaluate":[99],"our":[100,117],"method":[101],"across":[102,129],"multiple":[103],"continuous":[104],"control":[105],"environments":[106],"both":[108],"synthetic":[109],"oracles":[110],"human":[112,133],"trainers.":[113],"Results":[114],"show":[115],"accelerates":[119],"compared":[121],"standard":[123],"while":[126],"maintaining":[127],"robustness":[128],"different":[130],"types":[131],"of":[132],"patterns.":[135],"The":[136],"improved":[137],"speed":[139],"natural":[142],"interaction":[143],"suggest":[144],"this":[146],"promising":[149],"direction":[150],"for":[151],"making":[152],"human-in-the-loop":[153],"RL":[154],"practical.":[156]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}