{"id":"https://openalex.org/W4402673477","doi":"https://doi.org/10.1109/tnnls.2024.3443102","title":"Improving Offline Reinforcement Learning With in-Sample Advantage Regularization for Robot Manipulation","display_name":"Improving Offline Reinforcement Learning With in-Sample Advantage Regularization for Robot Manipulation","publication_year":2024,"publication_date":"2024-09-20","ids":{"openalex":"https://openalex.org/W4402673477","doi":"https://doi.org/10.1109/tnnls.2024.3443102","pmid":"https://pubmed.ncbi.nlm.nih.gov/39302799"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3443102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3443102","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061240255","display_name":"Chengzhong Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengzhong Ma","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0003-0835-4356","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102802634","display_name":"Deyu Yang","orcid":"https://orcid.org/0000-0001-5501-3253"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyu Yang","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101941291","display_name":"Tianyu Wu","orcid":"https://orcid.org/0000-0003-3448-2995"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Wu","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102893461","display_name":"Zeyang Liu","orcid":"https://orcid.org/0000-0002-3110-8618"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyang Liu","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-3110-8618","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108334208","display_name":"Houxue Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houxue Yang","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004275338","display_name":"Xingyu Chen","orcid":"https://orcid.org/0000-0002-5226-963X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Chen","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-5226-963X","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006277484","display_name":"Xuguang Lan","orcid":"https://orcid.org/0000-0002-3422-944X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-3422-944X","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-1608-8257","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":1.6671,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8640392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"36","issue":"6","first_page":"11215","last_page":"11227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9789999723434448,"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":0.9789999723434448,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9746000170707703,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.968500018119812,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7757269144058228},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5695494413375854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5341861248016357},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.518277108669281},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5062002539634705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45215508341789246},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4194268584251404},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.335606187582016},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20688262581825256},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07722711563110352},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05924409627914429},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.05419355630874634}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7757269144058228},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5695494413375854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5341861248016357},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.518277108669281},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5062002539634705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45215508341789246},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4194268584251404},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.335606187582016},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20688262581825256},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07722711563110352},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05924409627914429},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.05419355630874634}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3443102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3443102","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:39302799","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39302799","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1773090561","display_name":null,"funder_award_id":"62203348","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7207008540","display_name":null,"funder_award_id":"U23A20339","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8180423952","display_name":null,"funder_award_id":"62125305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2145339207","https://openalex.org/W2150339816","https://openalex.org/W2158782408","https://openalex.org/W2746553466","https://openalex.org/W2765302304","https://openalex.org/W2791797404","https://openalex.org/W2883972132","https://openalex.org/W2963669336","https://openalex.org/W2978455699","https://openalex.org/W2989186172","https://openalex.org/W2990747716","https://openalex.org/W3039055967","https://openalex.org/W3127561923","https://openalex.org/W3134231938","https://openalex.org/W3173984942","https://openalex.org/W3211583675","https://openalex.org/W4225710745","https://openalex.org/W4226257065","https://openalex.org/W4285222953","https://openalex.org/W4321015489","https://openalex.org/W4323767275","https://openalex.org/W4360584316","https://openalex.org/W4385430679","https://openalex.org/W6637967152","https://openalex.org/W6684338915","https://openalex.org/W6687045409","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6755015941","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6771270455","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6779463497","https://openalex.org/W6779656125","https://openalex.org/W6785308759","https://openalex.org/W6791413555","https://openalex.org/W6792049622","https://openalex.org/W6795014841","https://openalex.org/W6796289742","https://openalex.org/W6796589144","https://openalex.org/W6796926305","https://openalex.org/W6799150178","https://openalex.org/W6801801719","https://openalex.org/W6802659552","https://openalex.org/W6804244202","https://openalex.org/W6810030924","https://openalex.org/W6810602712","https://openalex.org/W6810906561","https://openalex.org/W6838240175","https://openalex.org/W6838356327","https://openalex.org/W6839066311","https://openalex.org/W6839344006","https://openalex.org/W6851312059","https://openalex.org/W6853588135"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,37],"(RL)":[3],"aims":[4],"to":[5,32,43,60,86,90,97,134,201],"learn":[6],"the":[7,18,22,26,35,58,61,65,73,118,123,126,131,136,143,163,183,195,206,221],"possible":[8],"policy":[9,59,164],"from":[10,48],"a":[11,156,175,227],"fixed":[12],"dataset":[13,132],"without":[14,205],"real-time":[15],"interactions":[16],"with":[17,93,111,130,170],"environment.":[19],"By":[20],"avoiding":[21],"risky":[23],"exploration":[24],"of":[25,69,75,120,146,182,223],"robot,":[27],"this":[28,82],"approach":[29],"is":[30,72],"expected":[31],"significantly":[33],"improve":[34,108],"robot's":[36],"efficiency":[38,169],"and":[39,78,96,154,177,187,212],"safety.":[40],"However,":[41],"due":[42],"errors":[44],"in":[45,162,174],"value":[46,152],"estimation":[47,153],"out-of-distribution":[49,100],"actions,":[50,122],"most":[51],"offline":[52,88,109],"RL":[53,89,110],"algorithms":[54,204],"constrain":[55],"or":[56],"regularize":[57],"actions":[62,101],"contained":[63],"within":[64],"dataset.":[66],"The":[67,180],"cost":[68],"such":[70],"methods":[71],"introduction":[74],"new":[76],"hyperparameters":[77],"additional":[79],"complexity.":[80],"In":[81,217],"article,":[83],"we":[84,107,219],"aim":[85],"adapt":[87],"robotic":[91,191],"manipulation":[92],"minimal":[94,171],"changes":[95],"avoid":[98],"evaluating":[99],"as":[102,104],"much":[103,214],"possible.":[105],"Therefore,":[106],"in-sample":[112,151],"advantage":[113,144],"regularization":[114,160],"(ISAR).":[115],"To":[116],"mitigate":[117],"impact":[119],"unseen":[121],"ISAR":[124,196],"learns":[125],"state-value":[127],"function":[128,145],"only":[129],"sample":[133,168],"regress":[135],"optimal":[137],"action-value":[138],"function.":[139],"Our":[140],"method":[141,225],"calculates":[142],"action-state":[147],"pairs":[148],"based":[149],"on":[150,226],"adds":[155],"behavior":[157],"cloning":[158],"(BC)":[159],"term":[161],"update.":[165],"This":[166],"improves":[167],"changes,":[172],"resulting":[173],"simple":[176],"easy-to-implement":[178],"method.":[179],"experiments":[181],"D4RL":[184],"robot":[185,229],"benchmark":[186],"multigoal":[188],"sparse":[189],"rewards":[190],"tasks":[192],"show":[193],"that":[194],"achieves":[197],"excellent":[198],"performance":[199],"comparable":[200],"current":[202],"state-of-the-art":[203],"need":[207],"for":[208],"complex":[209],"parameter":[210],"tuning":[211],"too":[213],"training":[215],"time.":[216],"addition,":[218],"demonstrate":[220],"effectiveness":[222],"our":[224],"real-world":[228],"platform.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}