{"id":"https://openalex.org/W4402352014","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650768","title":"Conservative In-Distribution Q-Learning for Offline Reinforcement Learning","display_name":"Conservative In-Distribution Q-Learning for Offline Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352014","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650768"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650768","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5072366496","display_name":"Zhengdao Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengdao Shao","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044163181","display_name":"Liansheng Zhuang","orcid":"https://orcid.org/0000-0002-4345-856X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liansheng Zhuang","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437838","display_name":"Jie Yan","orcid":"https://orcid.org/0000-0002-8800-6487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Yan","raw_affiliation_strings":["Step.ai,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Step.ai,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088627356","display_name":"Liting Chen","orcid":"https://orcid.org/0000-0002-7786-1226"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Liting Chen","raw_affiliation_strings":["McGill University,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University,Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9915000200271606,"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":0.8311961889266968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6878523826599121},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.46856406331062317},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4670146107673645},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.45820948481559753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4322616457939148},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3322122395038605},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1259714961051941},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09653094410896301},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07069399952888489}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8311961889266968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6878523826599121},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.46856406331062317},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4670146107673645},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.45820948481559753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4322616457939148},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3322122395038605},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1259714961051941},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09653094410896301},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07069399952888489},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650768","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":31,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1522301498","https://openalex.org/W2962756933","https://openalex.org/W2978455699","https://openalex.org/W2990138404","https://openalex.org/W3016506115","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W4281794919","https://openalex.org/W4294336468","https://openalex.org/W4304701438","https://openalex.org/W4317466250","https://openalex.org/W4366850766","https://openalex.org/W6631190155","https://openalex.org/W6748458661","https://openalex.org/W6751087324","https://openalex.org/W6763704811","https://openalex.org/W6763711611","https://openalex.org/W6771685344","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6791413555","https://openalex.org/W6796589144","https://openalex.org/W6802659552","https://openalex.org/W6810030924","https://openalex.org/W6838240175","https://openalex.org/W6845921359","https://openalex.org/W6851312059","https://openalex.org/W6851885053"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692"],"abstract_inverted_index":{"Offline":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"aims":[4],"to":[5,17,48,76,81],"learn":[6,77],"policies":[7],"from":[8,109],"pre-collected":[9],"datasets":[10],"without":[11],"any":[12],"additional":[13],"interaction.":[14],"In":[15],"order":[16],"perform":[18],"well":[19,38],"and":[20,33,40,89,121,123],"robustly":[21],"in":[22],"dynamic":[23],"environments":[24],"with":[25,79],"noise":[26],"or":[27],"disturbances,":[28],"the":[29,42,82],"learned":[30],"value":[31,94,100],"function":[32],"derived":[34],"policy":[35,110],"should":[36],"generalize":[37],"within":[39],"near":[41],"dataset":[43],"distribution,":[44],"rather":[45],"than":[46],"\u2018over-fitting\u2019":[47],"training":[49],"samples.":[50],"To":[51],"meet":[52],"this":[53],"requirement,":[54],"we":[55],"propose":[56],"a":[57,67,85,90],"new":[58],"approach":[59,113],"called":[60],"Conservative":[61],"In-Distribution":[62],"Q-learning":[63],"(CIDQL)":[64],"that":[65,106],"takes":[66],"step":[68],"towards":[69],"in-distribution":[70,78],"offline":[71],"RL.":[72],"CIDQL":[73],"is":[74,107],"designed":[75],"respect":[80],"dataset,":[83],"using":[84],"perturbation-based":[86],"interpolation":[87],"technique":[88],"quantile":[91],"method":[92],"for":[93,117],"regularization.":[95],"It":[96],"prohibits":[97],"bootstrapping":[98],"during":[99],"iteration,":[101],"ensuring":[102],"stable":[103],"Q-value":[104,119],"learning":[105],"separated":[108],"improvement.":[111],"The":[112],"has":[114],"theoretical":[115],"guarantees":[116],"both":[118],"underestimation":[120],"non-underestimation,":[122],"outperforms":[124],"most":[125],"SOTA":[126],"algorithms":[127],"on":[128],"D4RL":[129],"gym-MuJoCo":[130],"benchmarks.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}