{"id":"https://openalex.org/W6891904195","doi":"https://doi.org/10.48550/arxiv.2506.17564","title":"Accelerating Residual Reinforcement Learning with Uncertainty Estimation","display_name":"Accelerating Residual Reinforcement Learning with Uncertainty Estimation","publication_year":2025,"publication_date":"2025-06-21","ids":{"openalex":"https://openalex.org/W6891904195","doi":"https://doi.org/10.48550/arxiv.2506.17564"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2506.17564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.17564","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.2506.17564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dodeja, Lakshita","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dodeja, Lakshita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Schmeckpeper, Karl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schmeckpeper, Karl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Vats, Shivam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vats, Shivam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Weng, Thomas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weng, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jia, Mingxi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Mingxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Konidaris, George","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konidaris, George","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Tellex, Stefanie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tellex, Stefanie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"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":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":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9125000238418579,"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":0.9125000238418579,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0142000000923872,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01360000018030405,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.82669997215271},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.8163999915122986},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7421000003814697},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.673799991607666},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6392999887466431}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.82669997215271},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8163999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454000115394592},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7421000003814697},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.673799991607666},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6392999887466431},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49129998683929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4767000079154968},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.454800009727478},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.35370001196861267}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2506.17564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.17564","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.2506.17564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.17564","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":[{"display_name":"Peace, Justice and strong institutions","score":0.4908898174762726,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Residual":[0,23,52],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"is":[4,25,87],"a":[5,14,93,152],"popular":[6],"approach":[7],"for":[8,43,64],"adapting":[9],"pretrained":[10],"policies":[11,124],"by":[12],"learning":[13,99],"lightweight":[15],"residual":[16,98,142],"policy":[17,76,86],"that":[18,54,100],"provides":[19],"corrective":[20],"actions.":[21],"While":[22],"RL":[24,53,138,143],"more":[26],"sample-efficient":[27],"than":[28],"finetuning":[29,135],"the":[30,74,84,165],"entire":[31],"base":[32,45,66,75,85,105,111,123],"policy,":[33],"existing":[34,149],"methods":[35],"struggle":[36],"with":[37,117,172],"sparse":[38],"rewards":[39],"and":[40,60,107,120,129,131,140],"are":[41],"designed":[42],"deterministic":[44],"policies.":[46,67,112],"We":[47,113,158],"propose":[48,92],"two":[49],"improvements":[50],"to":[51,77,96,103,168],"further":[55],"enhance":[56],"its":[57],"sample":[58],"efficiency":[59],"make":[61],"it":[62,102],"suitable":[63],"stochastic":[65,110,122],"First,":[68],"we":[69,91],"leverage":[70],"uncertainty":[71],"estimates":[72],"of":[73,154],"focus":[78],"exploration":[79],"on":[80,125],"regions":[81],"in":[82,151,164],"which":[83],"not":[88],"confident.":[89],"Second,":[90],"simple":[94],"modification":[95],"off-policy":[97],"allows":[101],"observe":[104],"actions":[106],"better":[108],"handle":[109],"evaluate":[114],"our":[115,161],"method":[116],"both":[118],"Gaussian-based":[119],"Diffusion-based":[121],"tasks":[126],"from":[127],"Robosuite":[128],"D4RL,":[130],"compare":[132],"against":[133],"state-of-the-art":[134],"methods,":[136,139],"demo-augmented":[137],"other":[141],"methods.":[144],"Our":[145],"algorithm":[146],"significantly":[147],"outperforms":[148],"baselines":[150],"variety":[153],"simulation":[155],"benchmark":[156],"environments.":[157],"also":[159],"deploy":[160],"learned":[162],"polices":[163],"real":[166],"world":[167],"demonstrate":[169],"their":[170],"robustness":[171],"zero-shot":[173],"sim-to-real":[174],"transfer.":[175],"Paper":[176],"homepage":[177],":":[178],"lakshitadodeja.github.io/uncertainty-aware-residual-rl/":[179]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}