{"id":"https://openalex.org/W3004091789","doi":"https://doi.org/10.1109/iros40897.2019.8968254","title":"Structured Reward Shaping using Signal Temporal Logic specifications","display_name":"Structured Reward Shaping using Signal Temporal Logic specifications","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3004091789","doi":"https://doi.org/10.1109/iros40897.2019.8968254","mag":"3004091789"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8968254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5010081957","display_name":"Anand Balakrishnan","orcid":"https://orcid.org/0000-0002-8781-4810"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anand Balakrishnan","raw_affiliation_strings":["University of Southern California,Cyber-Physical Systems: Verification, Intelligence, Design and Analysis (CPS-VIDA) Group,Los Angeles,California","Cyber-Physical Systems: Verification, Intelligence, Design and Analysis (CPS-VIDA) Group, University of Southern California, Los Angeles, California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Cyber-Physical Systems: Verification, Intelligence, Design and Analysis (CPS-VIDA) Group,Los Angeles,California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Cyber-Physical Systems: Verification, Intelligence, Design and Analysis (CPS-VIDA) Group, University of Southern California, Los Angeles, California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057473400","display_name":"Jyotirmoy V. Deshmukh","orcid":"https://orcid.org/0000-0003-4683-5540"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyotirmoy V. Deshmukh","raw_affiliation_strings":["University of Southern California,Cyber-Physical Systems: Verification, Intelligence, Design and Analysis (CPS-VIDA) Group,Los Angeles,California","Cyber-Physical Systems: Verification, Intelligence, Design and Analysis (CPS-VIDA) Group, University of Southern California, Los Angeles, California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Cyber-Physical Systems: Verification, Intelligence, Design and Analysis (CPS-VIDA) Group,Los Angeles,California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Cyber-Physical Systems: Verification, Intelligence, Design and Analysis (CPS-VIDA) Group, University of Southern California, Los Angeles, California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010081957"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":4.6556,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.95443525,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3481","last_page":"3486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9991000294685364,"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":0.984499990940094,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.979200005531311,"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":0.7782111167907715},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7229212522506714},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.5841020345687866},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.5792914032936096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5158552527427673},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4718361496925354},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4189385771751404},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4181211590766907},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.41095179319381714},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.310164213180542},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2577948272228241},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08925855159759521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782111167907715},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7229212522506714},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.5841020345687866},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.5792914032936096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5158552527427673},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4718361496925354},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4189385771751404},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4181211590766907},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.41095179319381714},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.310164213180542},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2577948272228241},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08925855159759521},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros40897.2019.8968254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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":43,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W828139470","https://openalex.org/W1533557569","https://openalex.org/W1718202771","https://openalex.org/W1777239053","https://openalex.org/W1999874108","https://openalex.org/W2049399166","https://openalex.org/W2091565802","https://openalex.org/W2101804404","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2167799541","https://openalex.org/W2173248099","https://openalex.org/W2255983427","https://openalex.org/W2293761843","https://openalex.org/W2462906003","https://openalex.org/W2491675558","https://openalex.org/W2524638160","https://openalex.org/W2567705466","https://openalex.org/W2620974420","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2768908787","https://openalex.org/W2783378806","https://openalex.org/W2785700716","https://openalex.org/W2795231670","https://openalex.org/W2806088716","https://openalex.org/W2924373019","https://openalex.org/W2963864421","https://openalex.org/W3011120880","https://openalex.org/W3102942490","https://openalex.org/W3106462682","https://openalex.org/W6638088447","https://openalex.org/W6684921986","https://openalex.org/W6697224359","https://openalex.org/W6718836005","https://openalex.org/W6722970529","https://openalex.org/W6739055881","https://openalex.org/W6741002519","https://openalex.org/W6746721349","https://openalex.org/W6748367044","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W3009457412","https://openalex.org/W2992629954"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"has":[3],"become":[4],"a":[5,37,91,129,134,143],"popular":[6],"technique":[7,124],"to":[8,12,19,54,105,153],"train":[9],"autonomous":[10],"agents":[11],"learn":[13],"control":[14],"policies":[15],"that":[16,40,47,52],"enable":[17],"them":[18],"accomplish":[20],"complex":[21],"tasks":[22],"in":[23,51,109,166],"uncertain":[24],"environments.":[25],"A":[26],"key":[27],"component":[28],"of":[29,36,72,82,86,98,115,142],"an":[30,45,63],"RL":[31,156,171],"algorithm":[32],"is":[33,151],"the":[34,69,73,80,83,95,99,113,117,140],"definition":[35],"reward":[38,59],"function":[39],"maps":[41],"each":[42,110],"state":[43,53,111],"and":[44,138],"action":[46,136],"can":[48,162],"be":[49,163],"taken":[50],"some":[55],"real-valued":[56],"reward.":[57],"Typically,":[58],"functions":[60],"informally":[61],"capture":[62],"implicit":[64],"(albeit":[65],"vague)":[66],"specification":[67,93],"on":[68,125],"desired":[70,96],"behavior":[71],"agent.":[74,100],"In":[75],"this":[76],"paper,":[77],"we":[78,102],"propose":[79,103],"use":[81],"logical":[84],"formalism":[85],"Signal":[87],"Temporal":[88],"Logic(STL)":[89],"as":[90,158],"formal":[92],"for":[94,146],"behaviors":[97],"Furthermore,":[101],"algorithms":[104],"locally":[106,159],"shape":[107],"rewards":[108,161],"with":[112,133,168],"goal":[114],"satisfying":[116],"high-level":[118],"STL":[119],"specification.":[120],"We":[121],"demonstrate":[122],"our":[123],"two":[126],"case":[127],"studies,":[128],"cart-pole":[130],"balancing":[131],"problem":[132],"discrete":[135],"space,":[137],"controlling":[139],"actuation":[141],"simulated":[144],"quadrotor":[145],"point-to-point":[147],"movement.The":[148],"proposed":[149],"framework":[150],"agnostic":[152],"any":[154,169],"specific":[155],"algorithm,":[157],"shaped":[160],"easily":[164],"used":[165],"concert":[167],"deep":[170],"algorithm.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}