{"id":"https://openalex.org/W4403661740","doi":"https://doi.org/10.48550/arxiv.2409.08434","title":"Predictive Control and Regret Analysis of Non-Stationary MDP with Look-ahead Information","display_name":"Predictive Control and Regret Analysis of Non-Stationary MDP with Look-ahead Information","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4403661740","doi":"https://doi.org/10.48550/arxiv.2409.08434"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.08434","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08434","pdf_url":"https://arxiv.org/pdf/2409.08434","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.08434","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100352959","display_name":"Ziyi Zhang","orcid":"https://orcid.org/0009-0005-9492-3192","observed_orcids":["https://orcid.org/0009-0005-9492-3192","https://orcid.org/0009-0007-3433-6134"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Ziyi","raw_affiliation_strings":["Department of Electrical and Computer Engineering Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084147009","display_name":"Yorie Nakahira","orcid":"https://orcid.org/0000-0003-3324-4602","observed_orcids":["https://orcid.org/0000-0003-3324-4602"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nakahira, Yorie","raw_affiliation_strings":["Department of Electrical and Computer Engineering Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5094253784","display_name":"Guannan Qu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qu, Guannan","raw_affiliation_strings":["Department of Electrical and Computer Engineering Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8984000086784363,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8984000086784363,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.04230000078678131,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.027899999171495438,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/non-stationary-markov-decision-processes","display_name":"non-stationary Markov decision processes","score":0.9879999756813049},{"id":"https://openalex.org/keywords/regret-analysis","display_name":"regret analysis","score":0.8270000219345093},{"id":"https://openalex.org/keywords/predictive-control","display_name":"predictive control","score":0.8510000109672546},{"id":"https://openalex.org/keywords/renewable-energy-forecasting","display_name":"renewable energy forecasting","score":0.7179999947547913},{"id":"https://openalex.org/keywords/prediction-error","display_name":"prediction error","score":0.7379999756813049},{"id":"https://openalex.org/keywords/energy-systems","display_name":"energy systems","score":0.5320000052452087},{"id":"https://openalex.org/keywords/optimal-policy-design","display_name":"optimal policy design","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9578279256820679},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6200522184371948},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5122281908988953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4088950753211975},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.38610023260116577},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3504044711589813},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3152773380279541},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2919238209724426},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27480214834213257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1986498236656189}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.08434","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08434","pdf_url":"https://arxiv.org/pdf/2409.08434","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":"doi:10.48550/arxiv.2409.08434","doi":"https://doi.org/10.48550/arxiv.2409.08434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.08434","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.08434","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08434","pdf_url":"https://arxiv.org/pdf/2409.08434","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403661740.pdf","grobid_xml":"https://content.openalex.org/works/W4403661740.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3034465108","https://openalex.org/W3035038584","https://openalex.org/W3099984989","https://openalex.org/W4315472146","https://openalex.org/W7100531074","https://openalex.org/W3186418929","https://openalex.org/W4393372852","https://openalex.org/W7108756122","https://openalex.org/W2112576882","https://openalex.org/W4391152071"],"abstract_inverted_index":{"Policy":[0],"design":[1],"in":[2,39,76,139],"non-stationary":[3,77,140],"Markov":[4],"Decision":[5],"Processes":[6],"(MDPs)":[7],"is":[8,104],"inherently":[9],"challenging":[10],"due":[11],"to":[12,28,72,106],"the":[13,30,91,96,101,108,115,124,134],"complexities":[14],"introduced":[15],"by":[16,79],"time-varying":[17],"system":[18,102],"transition":[19],"and":[20,57,67],"reward,":[21],"which":[22],"make":[23],"it":[24],"difficult":[25],"for":[26,33,53],"learners":[27],"determine":[29],"optimal":[31],"actions":[32],"maximizing":[34],"cumulative":[35],"future":[36],"rewards.":[37],"Fortunately,":[38],"many":[40],"practical":[41],"applications,":[42],"such":[43,81],"as":[44,95,120],"energy":[45,55],"systems,":[46],"look-ahead":[47,65,97],"predictions":[48,66],"are":[49],"available,":[50],"including":[51],"forecasts":[52],"renewable":[54],"generation":[56],"demand.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"leverage":[63],"these":[64],"propose":[68],"an":[69],"algorithm":[70,138],"designed":[71],"achieve":[73],"low":[74],"regret":[75,92,109],"MDPs":[78],"incorporating":[80],"predictions.":[82],"Our":[83],"theoretical":[84],"analysis":[85],"demonstrates":[86],"that,":[87],"under":[88],"certain":[89],"assumptions,":[90],"decreases":[93],"exponentially":[94],"window":[98],"expands.":[99],"When":[100],"prediction":[103,116,125],"subject":[105],"error,":[107],"does":[110],"not":[111],"explode":[112],"even":[113],"if":[114],"error":[117],"grows":[118],"sub-exponentially":[119],"a":[121],"function":[122],"of":[123,136],"horizon.":[126],"We":[127],"validate":[128],"our":[129,137],"approach":[130],"through":[131],"simulations,":[132],"confirming":[133],"efficacy":[135],"environments.":[141]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-10-23T00:00:00"}