{"id":"https://openalex.org/W4400104547","doi":"https://doi.org/10.48550/arxiv.2406.18033","title":"Boosting Soft Q-Learning by Bounding","display_name":"Boosting Soft Q-Learning by Bounding","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400104547","doi":"https://doi.org/10.48550/arxiv.2406.18033"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.18033","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18033","pdf_url":"https://arxiv.org/pdf/2406.18033","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.18033","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084665220","display_name":"Jacob Adamczyk","orcid":"https://orcid.org/0000-0002-4628-3566","observed_orcids":["https://orcid.org/0000-0002-4628-3566"]},"institutions":[{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adamczyk, Jacob","raw_affiliation_strings":["Department of Physics University of Massachusetts Boston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics University of Massachusetts Boston","institution_ids":["https://openalex.org/I33434090"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069610293","display_name":"Volodymyr Makarenko","orcid":"https://orcid.org/0000-0003-1232-5198","observed_orcids":["https://orcid.org/0000-0003-1232-5198"]},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Makarenko, Volodymyr","raw_affiliation_strings":["Department of Computer Engineering San Jos\u00e9 State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering San Jos\u00e9 State University","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046771851","display_name":"Stas Tiomkin","orcid":"https://orcid.org/0000-0003-3677-6874","observed_orcids":["https://orcid.org/0000-0003-3677-6874"]},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiomkin, Stas","raw_affiliation_strings":["Department of Computer Engineering San Jos\u00e9 State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering San Jos\u00e9 State University","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048266570","display_name":"Rahul Kulkarni","orcid":"https://orcid.org/0000-0001-9333-8198","observed_orcids":["https://orcid.org/0000-0001-9333-8198"]},"institutions":[{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kulkarni, Rahul V.","raw_affiliation_strings":["Department of Physics University of Massachusetts Boston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics University of Massachusetts Boston","institution_ids":["https://openalex.org/I33434090"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":9.999999747378752e-05,"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":0.0,"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/soft-q-learning","display_name":"soft Q-learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/value-function-bounds","display_name":"value function bounds","score":0.699999988079071},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.6539999842643738},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.4950000047683716},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.3580000102519989},{"id":"https://openalex.org/keywords/optimal-value-function","display_name":"optimal value function","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.780340313911438},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7011884450912476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4610874056816101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4497140645980835}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.18033","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18033","pdf_url":"https://arxiv.org/pdf/2406.18033","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.2406.18033","doi":"https://doi.org/10.48550/arxiv.2406.18033","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.18033","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:2406.18033","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18033","pdf_url":"https://arxiv.org/pdf/2406.18033","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":[{"id":"https://openalex.org/G1550814497","display_name":"Large Deviations and Driven Processes for Stochastic Models of Gene Expression and Its Regulation","funder_award_id":"1854350","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1802981795","display_name":null,"funder_award_id":"195-2020","funder_id":"https://openalex.org/F4320325704","funder_display_name":"PAZY Foundation"},{"id":"https://openalex.org/G6768408121","display_name":"CRII: RI: Interpretable Framework and Transformative Applications for Viability in Autonomous Agents","funder_award_id":"2246221","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320313188","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275"},{"id":"https://openalex.org/F4320325704","display_name":"PAZY Foundation","ror":"https://ror.org/0412j5e72"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400104547.pdf","grobid_xml":"https://content.openalex.org/works/W4400104547.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3004055318","https://openalex.org/W3037207827","https://openalex.org/W4319988532"],"related_works":["https://openalex.org/W4321473463","https://openalex.org/W4388775936","https://openalex.org/W3137166149","https://openalex.org/W3208170749","https://openalex.org/W4402905713","https://openalex.org/W7124263497","https://openalex.org/W2963923407","https://openalex.org/W3034516888","https://openalex.org/W2945159000","https://openalex.org/W4407147140"],"abstract_inverted_index":{"An":[0],"agent's":[1],"ability":[2],"to":[3,23,29,47,60,87],"leverage":[4],"past":[5],"experience":[6],"is":[7],"critical":[8],"for":[9,27,63,82],"efficiently":[10],"solving":[11],"new":[12,31,61],"tasks.":[13],"Prior":[14],"work":[15],"has":[16],"focused":[17],"on":[18,51],"using":[19],"value":[20,40,54],"function":[21,41],"estimates":[22],"obtain":[24],"zero-shot":[25],"approximations":[26],"solutions":[28],"a":[30],"task.":[32],"In":[33],"soft":[34],"Q-learning,":[35],"we":[36,68,72],"show":[37],"how":[38],"any":[39],"estimate":[42],"can":[43],"also":[44],"be":[45],"used":[46],"derive":[48],"double-sided":[49],"bounds":[50,58],"the":[52,75,84],"optimal":[53],"function.":[55],"The":[56],"derived":[57],"lead":[59],"approaches":[62],"boosting":[64],"training":[65],"performance":[66],"which":[67],"validate":[69],"experimentally.":[70],"Notably,":[71],"find":[73],"that":[74],"proposed":[76],"framework":[77],"suggests":[78],"an":[79],"alternative":[80],"method":[81],"updating":[83],"Q-function,":[85],"leading":[86],"boosted":[88],"performance.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-06-28T00:00:00"}