{"id":"https://openalex.org/W7128719954","doi":"https://doi.org/10.48448/26w6-5w75","title":"Expressive Temporal Specifications for Reward Monitoring","display_name":"Expressive Temporal Specifications for Reward Monitoring","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128719954","doi":"https://doi.org/10.48448/26w6-5w75"},"language":"en","primary_location":{"id":"doi:10.48448/26w6-5w75","doi":"https://doi.org/10.48448/26w6-5w75","is_oa":true,"landing_page_url":"https://doi.org/10.48448/26w6-5w75","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/26w6-5w75","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004844714","display_name":"Omar Adalat","orcid":"https://orcid.org/0009-0003-6246-1769","observed_orcids":["https://orcid.org/0009-0003-6246-1769"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adalat, Omar","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055883955","display_name":"Francesco Belardinelli","orcid":"https://orcid.org/0000-0002-7768-1794","observed_orcids":["https://orcid.org/0000-0002-7768-1794"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Belardinelli, Francesco","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8690999746322632,"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":0.8690999746322632,"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/T10142","display_name":"Formal Methods in Verification","score":0.11020000278949738,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.007600000128149986,"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/sparse-rewards","display_name":"sparse rewards","score":0.9110000133514404},{"id":"https://openalex.org/keywords/long-horizon-decision-making","display_name":"long-horizon decision-making","score":0.7749999761581421},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5950000286102295},{"id":"https://openalex.org/keywords/runtime-monitoring","display_name":"runtime monitoring","score":0.40799999237060547},{"id":"https://openalex.org/keywords/task-completion","display_name":"task completion","score":0.6029999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494000196456909},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6729000210762024},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6290000081062317},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5404000282287598},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4968999922275543},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38350000977516174},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C187455244","wikidata":"https://www.wikidata.org/wiki/Q942353","display_name":"Boolean function","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2983497884","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite state","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2759999930858612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/26w6-5w75","doi":"https://doi.org/10.48448/26w6-5w75","is_oa":true,"landing_page_url":"https://doi.org/10.48448/26w6-5w75","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/26w6-5w75","doi":"https://doi.org/10.48448/26w6-5w75","is_oa":true,"landing_page_url":"https://doi.org/10.48448/26w6-5w75","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415893845","https://openalex.org/W3080730120","https://openalex.org/W4296963693","https://openalex.org/W4402502186","https://openalex.org/W4321062009","https://openalex.org/W2966537673","https://openalex.org/W7138316868","https://openalex.org/W7128357366","https://openalex.org/W2963190533","https://openalex.org/W7171029101"],"abstract_inverted_index":{"Specifying":[0],"informative":[1],"and":[2,67,94,102,133],"dense":[3,46],"reward":[4,41],"functions":[5],"remains":[6],"a":[7,45,98,127],"pivotal":[8],"challenge":[9],"in":[10,125,134],"Reinforcement":[11],"Learning,":[12],"as":[13],"it":[14],"directly":[15],"affects":[16],"the":[17,27,70,83,87,120],"efficiency":[18],"of":[19,30,48,73,130],"agent":[20],"training.":[21],"In":[22],"this":[23],"work,":[24],"we":[25],"harness":[26],"expressive":[28],"power":[29],"quantitative":[31,113,128],"Linear":[32],"Temporal":[33],"Logic":[34],"on":[35,97,119],"finite":[36],"traces":[37],"(($\\text{LTL}_f[\\mathcal{F}]$))":[38],"to":[39],"synthesize":[40],"monitors":[42,61,114,124],"that":[43,111],"generate":[44],"stream":[47],"rewards":[49,75],"for":[50],"runtime-observable":[51],"state":[52,99],"trajectories.":[53],"By":[54],"providing":[55],"nuanced":[56],"feedback":[57],"during":[58],"training,":[59],"these":[60],"guide":[62],"agents":[63],"toward":[64],"optimal":[65],"behaviour":[66],"help":[68],"mitigate":[69],"well-known":[71],"issue":[72],"sparse":[74],"under":[76,82],"long-horizon":[77],"decision":[78],"making,":[79],"which":[80],"arises":[81],"Boolean":[84,123],"semantics":[85],"dominating":[86],"current":[88],"literature.":[89],"Our":[90],"framework":[91],"is":[92],"algorithm-agnostic":[93],"only":[95],"relies":[96],"labelling":[100],"function,":[101],"naturally":[103],"accommodates":[104],"specifying":[105],"non-Markovian":[106],"properties.":[107],"Empirical":[108],"results":[109],"show":[110],"our":[112],"consistently":[115],"subsume":[116],"and,":[117],"depending":[118],"environment,":[121],"outperform":[122],"maximizing":[126],"measure":[129],"task":[131],"completion":[132],"reducing":[135],"convergence":[136],"time.":[137]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}