{"id":"https://openalex.org/W4396777539","doi":"https://doi.org/10.48550/arxiv.2405.01684","title":"Intelligent Switching for Reset-Free RL","display_name":"Intelligent Switching for Reset-Free RL","publication_year":2024,"publication_date":"2024-05-02","ids":{"openalex":"https://openalex.org/W4396777539","doi":"https://doi.org/10.48550/arxiv.2405.01684"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.01684","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.01684","pdf_url":"https://arxiv.org/pdf/2405.01684","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/2405.01684","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005200848","display_name":"Darshan Patil","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Patil, Darshan","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114056105","display_name":"Janarthanan Rajendran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rajendran, Janarthanan","raw_affiliation_strings":["Dalhousie University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045351810","display_name":"Glen Berseth","orcid":"https://orcid.org/0000-0001-7351-8028","observed_orcids":["https://orcid.org/0000-0001-7351-8028"]},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Berseth, Glen","raw_affiliation_strings":["CIFAR AI Chair","Universit\u00e9 de Montr\u00e9al Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIFAR AI Chair","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027720969","display_name":"Sarath Chandar","orcid":"https://orcid.org/0000-0002-9678-2830","observed_orcids":["https://orcid.org/0000-0002-9678-2830"]},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chandar, Sarath","raw_affiliation_strings":["CIFAR AI Chair","\u00c9cole Polytechnique de Montr\u00e9al Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIFAR AI Chair","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"\u00c9cole Polytechnique de Montr\u00e9al Canada","institution_ids":["https://openalex.org/I45683168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":1.0,"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":1.0,"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":0.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/termination-detection","display_name":"termination detection","score":0.4569999873638153},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.4300000071525574}],"concepts":[{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.9285838603973389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5033459067344666},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.17512565851211548},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2405.01684","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.01684","pdf_url":"https://arxiv.org/pdf/2405.01684","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:publications.polymtl.ca:66826","doi":null,"is_oa":true,"landing_page_url":"https://publications.polymtl.ca/66826/","pdf_url":"https://proceedings.iclr.cc/paper_files/paper/2024/file/23a081d2dbdeb531080ced0c2942103a-Paper-Conference.pdf","source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Patil, D., Rajendran, J., Berseth, G., & Anbil Parthipan, S. C. (2024, May). Intelligent Switching for Reset-Free RL [Paper]. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria.","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"doi:10.48550/arxiv.2405.01684","doi":"https://doi.org/10.48550/arxiv.2405.01684","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.01684","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.01684","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.01684","pdf_url":"https://arxiv.org/pdf/2405.01684","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320330273","display_name":"Institut de Valorisation des Donn\u00e9es","ror":"https://ror.org/05a3srq89"},{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396777539.pdf","grobid_xml":"https://content.openalex.org/works/W4396777539.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W350273603","https://openalex.org/W2393495588","https://openalex.org/W96259911","https://openalex.org/W2168225754","https://openalex.org/W4385608460","https://openalex.org/W2370772865","https://openalex.org/W1528611913","https://openalex.org/W2000034628"],"abstract_inverted_index":{"In":[0],"the":[1,4,23,29,40,67,71,77,82,114,119],"real":[2,30],"world,":[3,31],"strong":[5],"episode":[6],"resetting":[7],"mechanisms":[8,45],"that":[9,65,76],"are":[10,17,88],"needed":[11],"to":[12,35,52,70],"train":[13,53],"agents":[14,54,87,116],"in":[15,28,95,122],"simulation":[16],"unavailable.":[18],"The":[19],"\\textit{resetting}":[20],"assumption":[21],"limits":[22],"potential":[24],"of":[25,42,81],"reinforcement":[26],"learning":[27],"as":[32],"providing":[33],"resets":[34,58],"an":[36],"agent":[37,64,69],"usually":[38],"requires":[39],"creation":[41],"additional":[43],"handcrafted":[44],"or":[46],"human":[47],"interventions.":[48],"Recent":[49],"work":[50],"aims":[51],"(\\textit{forward})":[55],"with":[56,105],"learned":[57],"by":[59],"constructing":[60],"a":[61,99],"second":[62],"(\\textit{backward})":[63],"returns":[66],"forward":[68],"initial":[72],"state.":[73],"We":[74],"find":[75],"termination":[78],"and":[79],"timing":[80],"transitions":[83],"between":[84,113],"these":[85],"two":[86,115],"crucial":[89],"for":[90,137],"algorithm":[91],"success.":[92],"With":[93],"this":[94],"mind,":[96],"we":[97],"create":[98],"new":[100,128],"algorithm,":[101],"Reset":[102],"Free":[103],"RL":[104],"Intelligently":[106],"Switching":[107],"Controller":[108],"(RISC)":[109],"which":[110],"intelligently":[111],"switches":[112],"based":[117],"on":[118,133],"agent's":[120],"confidence":[121],"achieving":[123],"its":[124],"current":[125],"goal.":[126],"Our":[127],"method":[129],"achieves":[130],"state-of-the-art":[131],"performance":[132],"several":[134],"challenging":[135],"environments":[136],"reset-free":[138],"RL.":[139]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
