{"id":"https://openalex.org/W4286972819","doi":"https://doi.org/10.23919/acc53348.2022.9867395","title":"Soft Actor-Critic With Integer Actions","display_name":"Soft Actor-Critic With Integer Actions","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4286972819","doi":"https://doi.org/10.23919/acc53348.2022.9867395"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867395","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867395","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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 American Control Conference (ACC)","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/A5085851733","display_name":"Ting-Han Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]},{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ting-Han Fan","raw_affiliation_strings":["Princeton University,Department of Electrical and Computer Engineering,Princeton,NJ,08544","Siemens Technology, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"Princeton University,Department of Electrical and Computer Engineering,Princeton,NJ,08544","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Siemens Technology, Princeton, NJ","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383180","display_name":"Y\u00fcbo Wang","orcid":"https://orcid.org/0000-0001-8727-8213"},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yubo Wang","raw_affiliation_strings":["Siemens Technology,Princeton,NJ,08540"],"affiliations":[{"raw_affiliation_string":"Siemens Technology,Princeton,NJ,08540","institution_ids":["https://openalex.org/I4210137693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085851733"],"corresponding_institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210137693"],"apc_list":null,"apc_paid":null,"fwci":1.1427,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79891187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2611","last_page":"2616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9861000180244446,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.8314940929412842},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.7904112339019775},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7305139303207397},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.6530458927154541},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5540477633476257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5456554889678955},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5323470234870911},{"id":"https://openalex.org/keywords/comparability","display_name":"Comparability","score":0.4721814692020416},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45704537630081177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.411540150642395},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3075505495071411},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2781530022621155},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0954928994178772}],"concepts":[{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.8314940929412842},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7904112339019775},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7305139303207397},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.6530458927154541},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5540477633476257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5456554889678955},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5323470234870911},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.4721814692020416},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45704537630081177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.411540150642395},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3075505495071411},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2781530022621155},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0954928994178772},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc53348.2022.9867395","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867395","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W1976368602","https://openalex.org/W1977357978","https://openalex.org/W2046765929","https://openalex.org/W2119717200","https://openalex.org/W2155007355","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2164858444","https://openalex.org/W2242818861","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2613332842","https://openalex.org/W2615790994","https://openalex.org/W2736601468","https://openalex.org/W2769883686","https://openalex.org/W2781726626","https://openalex.org/W2786303200","https://openalex.org/W2787938642","https://openalex.org/W2893470574","https://openalex.org/W2963184939","https://openalex.org/W2963735467","https://openalex.org/W2981037657","https://openalex.org/W2997756832","https://openalex.org/W2997902164","https://openalex.org/W3177343494","https://openalex.org/W3197610447","https://openalex.org/W4287234522","https://openalex.org/W4287285122","https://openalex.org/W4287643854","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W4320517071","https://openalex.org/W6627932998","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6682849425","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6690026940","https://openalex.org/W6697501834","https://openalex.org/W6725939724","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6738596827","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6747993910","https://openalex.org/W6748839928","https://openalex.org/W6755137159","https://openalex.org/W6769218391","https://openalex.org/W6772421901","https://openalex.org/W6780559895","https://openalex.org/W6783840228","https://openalex.org/W6791533680","https://openalex.org/W6793999791","https://openalex.org/W6797024940","https://openalex.org/W6800868767"],"related_works":["https://openalex.org/W2365594754","https://openalex.org/W2575292835","https://openalex.org/W4287902769","https://openalex.org/W3001140700","https://openalex.org/W3021704418","https://openalex.org/W2995453361","https://openalex.org/W4390295458","https://openalex.org/W1990407237","https://openalex.org/W2092282998","https://openalex.org/W2053982300"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,29],"is":[2,10,50,73,86],"well-studied":[3],"under":[4,30,83],"discrete":[5,53],"actions.":[6],"Integer":[7],"actions":[8,32,49,85],"setting":[9],"popular":[11],"in":[12],"the":[13,35,63,80,90],"industry":[14],"yet":[15],"still":[16],"challenging":[17],"due":[18],"to":[19],"its":[20],"high":[21],"dimensionality.":[22,76],"To":[23],"this":[24],"end,":[25],"we":[26],"study":[27],"reinforcement":[28],"integer":[31,42,48,65,84],"by":[33],"incorporating":[34],"Soft":[36],"Actor-Critic":[37],"(SAC)":[38],"algorithm":[39],"with":[40],"an":[41],"reparameterization.":[43],"Our":[44],"key":[45],"observation":[46],"for":[47],"that":[51,79],"their":[52,59],"structure":[54],"can":[55],"be":[56],"simplified":[57],"using":[58],"comparability":[60],"property.":[61],"Hence,":[62],"proposed":[64,81],"reparameterization":[66],"does":[67],"not":[68],"need":[69],"one-hot":[70],"encoding":[71],"and":[72,98],"of":[74],"low":[75],"Experiments":[77],"show":[78],"SAC":[82],"as":[87,89],"good":[88],"continuous":[91],"action":[92],"version":[93],"on":[94,103],"robot":[95],"control":[96,107],"tasks":[97],"outperforms":[99],"Proximal":[100],"Policy":[101],"Optimization":[102],"power":[104],"distribution":[105],"systems":[106],"tasks.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
