{"id":"https://openalex.org/W4399657728","doi":"https://doi.org/10.48550/arxiv.2406.08395","title":"Time-Constrained Robust MDPs","display_name":"Time-Constrained Robust MDPs","publication_year":2024,"publication_date":"2024-06-12","ids":{"openalex":"https://openalex.org/W4399657728","doi":"https://doi.org/10.48550/arxiv.2406.08395"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2406.08395","pdf_url":"https://arxiv.org/pdf/2406.08395","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.08395","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019608057","display_name":"Adil Zouitine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zouitine, Adil","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036340153","display_name":"David Bertoin","orcid":"https://orcid.org/0000-0003-3858-3881"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bertoin, David","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113950734","display_name":"Pierre J. Clavier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clavier, Pierre","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geist, Matthieu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049708660","display_name":"Emmanuel Rachelson","orcid":"https://orcid.org/0000-0002-8559-1617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rachelson, Emmanuel","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":84},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.7837,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.7837,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.7515,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.7352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49812937}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2406.08395","pdf_url":"https://arxiv.org/pdf/2406.08395","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2406.08395","pdf_url":"https://arxiv.org/pdf/2406.08395","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4396701345","https://openalex.org/W4396696052","https://openalex.org/W4395014643","https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2382290278","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Robust":[0],"reinforcement":[1,7,19],"learning":[2,8,20],"is":[3],"essential":[4],"for":[5,96,161],"deploying":[6],"algorithms":[9,124],"in":[10,47,139,145,154],"real-world":[11,78],"scenarios":[12],"where":[13,26],"environmental":[14,109],"uncertainty":[15],"predominates.":[16],"Traditional":[17],"robust":[18,63,97,136,155],"often":[21],"depends":[22],"on":[23,115],"rectangularity":[24,86],"assumptions,":[25],"adverse":[27],"probability":[28],"measures":[29],"of":[30,108],"outcome":[31],"states":[32,40],"are":[33],"assumed":[34],"to":[35,50],"be":[36],"independent":[37],"across":[38],"different":[39],"and":[41,71,91,111,131,157,165],"actions.":[42],"This":[43,80,148],"assumption,":[44],"rarely":[45],"fulfilled":[46],"practice,":[48],"leads":[49],"overly":[51],"conservative":[52],"policies.":[53],"To":[54],"address":[55],"this":[56],"problem,":[57],"we":[58],"introduce":[59],"a":[60],"new":[61,89,159],"time-constrained":[62,140],"MDP":[64],"(TC-RMDP)":[65],"formulation":[66,81],"that":[67,122],"considers":[68],"multifactorial,":[69],"correlated,":[70],"time-dependent":[72],"disturbances,":[73],"thus":[74],"more":[75,163],"accurately":[76],"reflecting":[77],"dynamics.":[79],"goes":[82],"beyond":[83],"the":[84,93,151],"conventional":[85],"paradigm,":[87],"offering":[88],"perspectives":[90],"expanding":[92],"analytical":[94],"framework":[95],"RL.":[98],"We":[99],"propose":[100],"three":[101],"distinct":[102],"algorithms,":[103],"each":[104],"using":[105],"varying":[106],"levels":[107],"information,":[110],"evaluate":[112],"them":[113],"extensively":[114],"continuous":[116],"control":[117],"benchmarks.":[118,147],"Our":[119],"results":[120],"demonstrate":[121],"these":[123],"yield":[125],"an":[126],"efficient":[127],"tradeoff":[128],"between":[129],"performance":[130],"robustness,":[132],"outperforming":[133],"traditional":[134],"deep":[135],"RL":[137,156,167],"methods":[138],"environments":[141],"while":[142],"preserving":[143],"robustness":[144],"classical":[146],"study":[149],"revisits":[150],"prevailing":[152],"assumptions":[153],"opens":[158],"avenues":[160],"developing":[162],"practical":[164],"realistic":[166],"applications.":[168]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4399657728","counts_by_year":[],"updated_date":"2024-12-15T08:45:59.591536","created_date":"2024-06-14"}