{"id":"https://openalex.org/W7212037684","doi":"https://doi.org/10.48550/arxiv.2609.07998","title":"Mini-Batch Risk-Averse Deep Q-Learning: A Robot Navigation Case Study","display_name":"Mini-Batch Risk-Averse Deep Q-Learning: A Robot Navigation Case Study","publication_year":2026,"publication_date":"2026-09-07","ids":{"openalex":"https://openalex.org/W7212037684","doi":"https://doi.org/10.48550/arxiv.2609.07998"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.07998","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07998","pdf_url":"https://arxiv.org/pdf/2609.07998","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":"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/2609.07998","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5150909259","display_name":"Aayush Patel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patel, Aayush","raw_affiliation_strings":["Department of Management Science and Information Systems , Rutgers University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Management Science and Information Systems , Rutgers University ,","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014600365","display_name":"Andrzej Ruszczy\u0144ski","orcid":"https://orcid.org/0000-0002-4571-1469","observed_orcids":["https://orcid.org/0000-0002-4571-1469"]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruszczy\u0144ski, Andrzej","raw_affiliation_strings":["Department of Management Science and Information Systems , Rutgers University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Management Science and Information Systems , Rutgers University ,","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102322142"],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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":0.0024999999441206455,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/double-deep-q-network","display_name":"double deep Q-network","score":0.7620000243186951},{"id":"https://openalex.org/keywords/coherent-risk-measures","display_name":"coherent risk measures","score":0.7559999823570251},{"id":"https://openalex.org/keywords/underwater-robot-navigation","display_name":"underwater robot navigation","score":0.746999979019165},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6990000009536743},{"id":"https://openalex.org/keywords/distributional-robustness","display_name":"distributional robustness","score":0.7289999723434448},{"id":"https://openalex.org/keywords/hierarchical-control","display_name":"hierarchical control","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5496000051498413},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5447999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5139999985694885},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.47909998893737793},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3537999987602234},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33480000495910645},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.31029999256134033},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C106666656","wikidata":"https://www.wikidata.org/wiki/Q6771323","display_name":"Markov kernel","level":5,"score":0.25769999623298645},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.07998","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07998","pdf_url":"https://arxiv.org/pdf/2609.07998","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.07998","doi":"https://doi.org/10.48550/arxiv.2609.07998","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.07998","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:2609.07998","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07998","pdf_url":"https://arxiv.org/pdf/2609.07998","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212037684.pdf","grobid_xml":"https://content.openalex.org/works/W7212037684.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2154190222","https://openalex.org/W2995459009","https://openalex.org/W7160054705"],"related_works":["https://openalex.org/W4413914922","https://openalex.org/W6996254028","https://openalex.org/W7160054705","https://openalex.org/W4385451941","https://openalex.org/W4308503814","https://openalex.org/W2783797945","https://openalex.org/W4414582023","https://openalex.org/W2945850646","https://openalex.org/W7133185151","https://openalex.org/W3152257860"],"abstract_inverted_index":{"We":[0,66,118],"study":[1],"the":[2,10,49,76,81,90,128,148,187,206,218,221,224,234,249,253,262,269],"control":[3],"of":[4,12,84,105,108,131,150,189,220,252,268],"Markov":[5,21],"decision":[6],"processes":[7],"in":[8,52,163,243],"which":[9,164],"quality":[11],"a":[13,18,43,53,62,106,123,138,165],"policy":[14],"is":[15,41,78,92,97,155,264],"evaluated":[16],"by":[17,26,70],"dynamic,":[19],"time-consistent":[20],"risk":[22,45,74,188,273],"measure":[23,83],"rather":[24],"than":[25],"an":[27,102,114,158,198],"expected":[28,103],"discounted":[29],"cost.":[30],"The":[31,94,153],"main":[32],"obstacle":[33,69],"to":[34,80,143,157,186,197,205,238],"combining":[35],"such":[36],"measures":[37,274],"with":[38],"reinforcement":[39],"learning":[40,204],"that":[42,134],"transition":[44,50,73],"mapping":[46,77,96,121],"depends":[47],"on":[48,230],"kernel":[51],"nonlinear":[54],"way,":[55],"and":[56,89,136,175,202,245,275],"therefore":[57],"cannot":[58],"be":[59],"estimated":[60],"from":[61],"single":[63],"observed":[64],"transition.":[65],"remove":[67],"this":[68,120],"employing":[71],"mini-batch":[72],"mappings:":[75],"applied":[79,156],"empirical":[82,266],"$N$":[85,109],"independent":[86],"next-state":[87,110],"samples,":[88],"result":[91],"averaged.":[93],"resulting":[95,235],"again":[98],"coherent.":[99],"However,":[100],"as":[101],"value":[104],"function":[107],"values,":[111],"it":[112],"admits":[113],"unbiased":[115],"one-sample":[116],"estimator.":[117],"embed":[119],"into":[122],"double":[124],"deep":[125],"Q-network,":[126],"analyze":[127],"two":[129],"sources":[130],"estimation":[132],"bias":[133],"arise,":[135],"obtain":[137],"risk-averse":[139],"Q-learning":[140],"method":[141,154],"applicable":[142],"state":[144],"spaces":[145],"far":[146],"beyond":[147],"reach":[149],"tabular":[151],"schemes.":[152],"underwater":[159],"robot":[160],"navigation":[161],"problem,":[162,222],"vehicle":[166],"must":[167],"visit":[168],"collection":[169],"points,":[170,180],"gather":[171],"stochastic":[172],"information":[173],"payloads,":[174],"deliver":[176],"them":[177],"at":[178,183],"transmission":[179],"while":[181,256],"exposed":[182],"each":[184],"step":[185],"destruction.":[190],"A":[191,212],"hierarchical":[192],"decomposition":[193],"delegates":[194],"path":[195],"execution":[196],"exact":[199],"graph":[200],"search":[201],"confines":[203],"high-level":[207],"``collect":[208],"or":[209],"transmit''":[210],"decision.":[211],"low-dimensional":[213],"feature":[214],"map,":[215],"invariant":[216],"under":[217],"symmetries":[219],"replaces":[223],"raw":[225],"state--configuration":[226],"encoding.":[227],"In":[228],"experiments":[229],"$300$":[231],"held-out":[232],"environments,":[233],"policies":[236],"transfer":[237],"instance":[239],"sizes":[240],"never":[241],"seen":[242],"training,":[244],"already":[246],"$N=2$":[247],"reduces":[248],"upper":[250],"semideviation":[251],"outcome":[254],"distribution":[255],"simultaneously":[257],"improving":[258],"its":[259],"mean":[260],"whenever":[261],"simulator":[263],"misspecified---an":[265],"counterpart":[267],"duality":[270],"between":[271],"coherent":[272],"distributional":[276],"robustness.":[277]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-10T00:00:00"}