{"id":"https://openalex.org/W4413392820","doi":"https://doi.org/10.23919/acc63710.2025.11107721","title":"Generalized Advantage Estimation for Distributional Policy Gradients","display_name":"Generalized Advantage Estimation for Distributional Policy Gradients","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413392820","doi":"https://doi.org/10.23919/acc63710.2025.11107721"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107721","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5089662595","display_name":"Shahil Shaik","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shahil Shaik","raw_affiliation_strings":["Clemson University,Mechanical Engineering Department"],"affiliations":[{"raw_affiliation_string":"Clemson University,Mechanical Engineering Department","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036239586","display_name":"Jonathon M. Smereka","orcid":"https://orcid.org/0000-0001-9262-1143"},"institutions":[{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I1304082316","display_name":"United States Department of the Army","ror":"https://ror.org/035w1gb98","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathon M. Smereka","raw_affiliation_strings":["Ground Vehicle Systems Center U.S. Army CCDC"],"affiliations":[{"raw_affiliation_string":"Ground Vehicle Systems Center U.S. Army CCDC","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I1304082316"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100666595","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0001-5918-7525"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Clemson University,Mechanical Engineering Department"],"affiliations":[{"raw_affiliation_string":"Clemson University,Mechanical Engineering Department","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089662595"],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":8.7316,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97381747,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3073","last_page":"3078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10804","display_name":"Health Systems, Economic Evaluations, Quality of Life","score":0.8629000186920166,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10804","display_name":"Health Systems, Economic Evaluations, Quality of Life","score":0.8629000186920166,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10007","display_name":"Monetary Policy and Economic Impact","score":0.8391000032424927,"subfield":{"id":"https://openalex.org/subfields/2000","display_name":"General Economics, Econometrics and Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.7842000126838684,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6961719989776611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5250399112701416},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.38086533546447754},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.22752514481544495}],"concepts":[{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6961719989776611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5250399112701416},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.38086533546447754},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.22752514481544495},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107721","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309652","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2765302304","https://openalex.org/W2951360122","https://openalex.org/W2973229164","https://openalex.org/W3177063094","https://openalex.org/W4255839052"],"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":{"Generalized":[0],"Advantage":[1],"Estimation":[2],"(GAE)":[3],"has":[4],"been":[5],"used":[6],"to":[7,26,41,46,62,80,109,115,169],"mitigate":[8],"the":[9,23,28,52,76,89,92,99,164,171],"computational":[10],"complexity":[11],"of":[12,22],"reinforcement":[13],"learning":[14],"(RL)":[15],"by":[16],"employing":[17],"an":[18],"exponentially":[19,100],"weighted":[20,101],"estimation":[21,140],"advantage":[24,124,139],"function":[25],"reduce":[27],"variance":[29],"in":[30,55],"policy":[31,133,142,150],"gradient":[32,134,151],"estimates.":[33],"Despite":[34],"its":[35],"effectiveness,":[36],"GAE":[37,112,168],"is":[38,58],"not":[39],"designed":[40],"handle":[42],"value":[43],"distributions":[44],"integral":[45],"distributional":[47,111],"RL,":[48],"which":[49,86],"can":[50],"capture":[51],"inherent":[53],"stochasticity":[54],"systems":[56],"and":[57,91,161],"hence":[59],"more":[60],"robust":[61],"system":[63],"noises.":[64],"To":[65],"address":[66],"this":[67,105],"gap,":[68],"we":[69,103],"propose":[70],"a":[71,82,122],"novel":[72],"approach":[73],"that":[74,136],"utilizes":[75],"optimal":[77],"transport":[78],"theory":[79],"introduce":[81],"Wasserstein-like":[83,106],"directional":[84,93,107],"metric,":[85],"measures":[87],"both":[88],"distance":[90],"discrepancies":[94],"between":[95],"probability":[96],"distributions.":[97],"Using":[98],"estimation,":[102],"leverage":[104],"metric":[108],"derive":[110],"(DGAE).":[113],"Similar":[114],"traditional":[116,167],"GAE,":[117],"our":[118],"proposed":[119],"DGAE":[120,146],"provides":[121],"low-variance":[123],"estimate":[125],"with":[126,163,166],"controlled":[127],"bias,":[128],"making":[129],"it":[130],"well-suited":[131],"for":[132,141],"algorithms":[135],"rely":[137],"on":[138],"updates.":[143],"We":[144],"integrated":[145],"into":[147],"three":[148],"different":[149],"methods.":[152],"Algorithms":[153],"were":[154],"evaluated":[155],"across":[156],"various":[157],"OpenAI":[158],"Gym":[159],"environments":[160],"compared":[162],"baselines":[165],"assess":[170],"performance.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}