{"id":"https://openalex.org/W7225145990","doi":"https://doi.org/10.48550/arxiv.2611.02809","title":"Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment","display_name":"Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225145990","doi":"https://doi.org/10.48550/arxiv.2611.02809"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02809","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02809","pdf_url":"https://arxiv.org/pdf/2611.02809","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116098818","display_name":"Tristan Leuridan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210134356","display_name":"Laboratoire G\u00e9nie Industriel","ror":"https://ror.org/0455wwj08","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210134356"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Leuridan, Tristan","raw_affiliation_strings":["LGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LGI","institution_ids":["https://openalex.org/I4210134356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160395578","display_name":"Yiping Fang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210134356","display_name":"Laboratoire G\u00e9nie Industriel","ror":"https://ror.org/0455wwj08","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210134356"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fang, Yiping","raw_affiliation_strings":["LGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LGI","institution_ids":["https://openalex.org/I4210134356"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058202685","display_name":"Adam Abdin","orcid":"https://orcid.org/0000-0003-4645-0640","observed_orcids":["https://orcid.org/0000-0003-4645-0640"]},"institutions":[{"id":"https://openalex.org/I4210134356","display_name":"Laboratoire G\u00e9nie Industriel","ror":"https://ror.org/0455wwj08","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210134356"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Abdin, Adam","raw_affiliation_strings":["LGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LGI","institution_ids":["https://openalex.org/I4210134356"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210134356"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11701","display_name":"Space Satellite Systems and Control","score":0.3637999892234802,"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"}},"topics":[{"id":"https://openalex.org/T11701","display_name":"Space Satellite Systems and Control","score":0.3637999892234802,"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"}},{"id":"https://openalex.org/T11082","display_name":"Spacecraft Dynamics and Control","score":0.24230000376701355,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2223999947309494,"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/walker-constellation","display_name":"Walker constellation","score":0.8029999732971191},{"id":"https://openalex.org/keywords/approximate-dynamic-programming","display_name":"approximate dynamic programming","score":0.8759999871253967},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9369999766349792},{"id":"https://openalex.org/keywords/launch-failure","display_name":"launch failure","score":0.7450000047683716},{"id":"https://openalex.org/keywords/space-logistics","display_name":"space logistics","score":0.7889999747276306},{"id":"https://openalex.org/keywords/linear-function-approximation","display_name":"linear function approximation","score":0.8730000257492065}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8804000020027161},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7382000088691711},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6933000087738037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6488000154495239},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6154999732971191},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.5654000043869019},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5557000041007996},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.550000011920929},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5074999928474426},{"id":"https://openalex.org/C70352696","wikidata":"https://www.wikidata.org/wiki/Q8928","display_name":"Constellation","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C196644772","wikidata":"https://www.wikidata.org/wiki/Q3884964","display_name":"Orbit (dynamics)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3628999888896942},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C2779784338","wikidata":"https://www.wikidata.org/wiki/Q967145","display_name":"Satellite constellation","level":3,"score":0.3257000148296356},{"id":"https://openalex.org/C150325174","wikidata":"https://www.wikidata.org/wiki/Q4335500","display_name":"Optimal decision","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C3018325918","wikidata":"https://www.wikidata.org/wiki/Q663611","display_name":"Low earth orbit","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C141042865","wikidata":"https://www.wikidata.org/wiki/Q200125","display_name":"Expected value","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C189069379","wikidata":"https://www.wikidata.org/wiki/Q218124","display_name":"Ground track","level":4,"score":0.2720000147819519},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2987528665","wikidata":"https://www.wikidata.org/wiki/Q854845","display_name":"Earth observation satellite","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2611.02809","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02809","pdf_url":"https://arxiv.org/pdf/2611.02809","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05845741v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05845741","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"3rd Conference on AI in and for Space (SPAICE 2026), European Space Agency (ESA), Oct 2026, Noordwijk, Netherlands","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2611.02809","doi":"https://doi.org/10.48550/arxiv.2611.02809","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02809","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.02809","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02809","pdf_url":"https://arxiv.org/pdf/2611.02809","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5378999710083008,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322263","display_name":"Conseil R\u00e9gional, \u00cele-de-France","ror":"https://ror.org/04ry1rt27"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225145990.pdf","grobid_xml":"https://content.openalex.org/works/W7225145990.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415314712","https://openalex.org/W4388225464","https://openalex.org/W7033603788","https://openalex.org/W4412383954","https://openalex.org/W4405103619","https://openalex.org/W2786168385","https://openalex.org/W4409581232","https://openalex.org/W4415196107","https://openalex.org/W4417438707","https://openalex.org/W4309775098"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,31,102,106],"reinforcement":[4],"learning-based":[5],"approximate":[6,52,110],"dynamic":[7,111],"programming":[8,112],"approach":[9],"to":[10,68,85],"optimize":[11],"the":[12,28,50,71],"deployment":[13,92],"of":[14,95,101,109],"Walker-type":[15],"satellite":[16,24,46],"constellations":[17],"under":[18],"uncertainties,":[19],"including":[20],"launch":[21],"failures":[22],"and":[23,44,64,73,91],"malfunctions.":[25],"We":[26,48],"formulate":[27],"problem":[29],"as":[30],"Markov":[32],"Decision":[33],"Process":[34],"that":[35],"incorporates":[36],"low-injection":[37],"orbit":[38,42],"launches,":[39],"continuous":[40],"low-thrust":[41],"raising,":[43],"variable":[45],"loads.":[47],"adopt":[49],"offline":[51],"value":[53],"iteration":[54],"solution":[55],"method,":[56],"using":[57],"linear":[58],"function":[59],"approximation":[60],"with":[61,87],"basis":[62],"functions":[63],"action":[65],"pruning":[66],"strategies":[67],"substantially":[69],"reduce":[70],"computational":[72],"memory":[74],"requirements":[75],"for":[76],"finding":[77],"optimal":[78],"decision":[79],"policies.":[80],"Preliminary":[81],"results":[82],"demonstrate":[83],"convergence":[84],"policies":[86],"low":[88],"expected":[89],"costs":[90],"times,":[93],"both":[94],"which":[96],"are":[97],"lower":[98],"than":[99],"those":[100],"rolling-horizon":[103],"baseline,":[104],"showcasing":[105],"novel":[107],"application":[108],"in":[113],"space":[114],"logistics.":[115]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}