{"id":"https://openalex.org/W7168360632","doi":"https://doi.org/10.48550/arxiv.2607.12590","title":"Environment Parameter Gradient Theorem for Policy-Environment Co-Design in Reinforcement Learning","display_name":"Environment Parameter Gradient Theorem for Policy-Environment Co-Design in Reinforcement Learning","publication_year":2026,"publication_date":"2026-07-14","ids":{"openalex":"https://openalex.org/W7168360632","doi":"https://doi.org/10.48550/arxiv.2607.12590"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.12590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.12590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140757918","display_name":"Amber Srivastava","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Srivastava, Amber","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5140757918"],"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":0.5911999940872192,"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":0.5911999940872192,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.10300000011920929,"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/T11133","display_name":"UAV Applications and Optimization","score":0.0843999981880188,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8068000078201294},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.6013000011444092},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5184999704360962},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5181000232696533},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5060999989509583},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4449000060558319},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.38960000872612},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.35910001397132874}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8068000078201294},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5631999969482422},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35910001397132874},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2777000069618225},{"id":"https://openalex.org/C55524764","wikidata":"https://www.wikidata.org/wiki/Q515173","display_name":"Contraction mapping","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C163415756","wikidata":"https://www.wikidata.org/wiki/Q126473","display_name":"Contraction (grammar)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.12590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.12590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,7],"(RL)":[2],"is":[3,23,85,126],"traditionally":[4],"concerned":[5],"with":[6,76],"a":[8,12,66,86,120,138,159],"control":[9],"policy":[10,49,146],"for":[11,69],"fixed":[13],"environment.":[14],"In":[15],"many":[16],"engineering":[17],"systems,":[18],"however,":[19],"the":[20,34,41,48,51,70,73,96,101,107,114,129,144,148,153,165,176,183,188],"environment":[21,52,79,97,149],"itself":[22],"alterable:":[24],"physical":[25],"or":[26],"operational":[27],"parameters":[28],"can":[29],"be":[30],"tuned":[31],"to":[32,78,128,181],"shape":[33],"transition":[35,104],"dynamics":[36,105],"and":[37,50,103,125,147,171],"costs":[38],"experienced":[39],"by":[40,175],"agent.":[42],"This":[43,117],"motivates":[44],"jointly":[45,180],"optimizing":[46],"both":[47],"design":[53,162],"parameters.":[54,80,150],"To":[55],"this":[56,134],"end,":[57],"we":[58,136],"establish":[59],"an":[60],"Environment":[61],"Parameter":[62],"Gradient":[63],"Theorem":[64],"--":[65],"formal":[67],"expression":[68,124],"gradient":[71,123],"of":[72,95,155],"value":[74],"function":[75,89],"respect":[77],"The":[81],"key":[82],"theoretical":[83],"device":[84],"generalized":[87],"action-value":[88],"$Q_{\u03c0,\u03be}(s,a,\u03b6)$,":[90],"which":[91],"comprises":[92],"two":[93],"copies":[94],"parameters:":[98],"$\u03b6$":[99],"governs":[100,113],"cost":[102,186],"at":[106],"current":[108],"state--action":[109],"pair,":[110],"while":[111],"$\u03be$":[112],"future":[115],"rollouts.":[116],"decoupling":[118],"yields":[119],"tractable":[121],"closed-form":[122],"essential":[127],"theorem's":[130],"derivation.":[131],"Building":[132],"on":[133,158],"result,":[135],"develop":[137],"model-free":[139],"algorithm":[140],"that":[141],"simultaneously":[142],"learns":[143],"optimal":[145,166],"We":[151],"demonstrate":[152],"efficacy":[154],"our":[156],"framework":[157],"UAV":[160,167],"network":[161],"problem,":[163],"where":[164],"placement":[168],"(environment":[169],"parameters)":[170],"communication":[172,185],"routes":[173],"(governed":[174],"policy)":[177],"are":[178],"learned":[179],"minimize":[182],"total":[184],"in":[187],"network.":[189]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-16T00:00:00"}