{"id":"https://openalex.org/W7133200833","doi":"https://doi.org/10.52202/068431-1319","title":"MoCoDA: Model-Based Counterfactual Data Augmentation","display_name":"MoCoDA: Model-Based Counterfactual Data Augmentation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7133200833","doi":"https://doi.org/10.52202/068431-1319"},"language":"en","primary_location":{"id":"doi:10.52202/068431-1319","doi":"https://doi.org/10.52202/068431-1319","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-1319","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 35","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.11287","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010938443","display_name":"Silviu Pitis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Silviu Pitis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029835581","display_name":"Elliot Creager","orcid":"https://orcid.org/0009-0004-7122-3866","observed_orcids":["https://orcid.org/0009-0004-7122-3866"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elliot Creager","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026180478","display_name":"Ajay Mandlekar","orcid":"https://orcid.org/0009-0008-5448-5011","observed_orcids":["https://orcid.org/0009-0008-5448-5011"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ajay Mandlekar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296","observed_orcids":["https://orcid.org/0000-0003-0482-4296"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Animesh Garg","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":1.1746,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.83015242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"18143","last_page":"18156"},"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/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.8659999966621399},{"id":"https://openalex.org/keywords/counterfactual-data-augmentation","display_name":"counterfactual data augmentation","score":0.9750000238418579},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.5960000157356262},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.9750000238418579},{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.8090000152587891}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40310001373291016},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.301800012588501},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27570000290870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23929999768733978},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2363000065088272},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2160000056028366},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2134999930858612},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2110999971628189}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/068431-1319","doi":"https://doi.org/10.52202/068431-1319","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-1319","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 35","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.11287","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.11287","pdf_url":"https://arxiv.org/pdf/2210.11287","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.11287","doi":"https://doi.org/10.48550/arxiv.2210.11287","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.11287","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.11287","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.11287","pdf_url":"https://arxiv.org/pdf/2210.11287","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"},{"id":"https://openalex.org/F4320322015","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133200833.pdf","grobid_xml":"https://content.openalex.org/works/W7133200833.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2964121744","https://openalex.org/W3022566517"],"related_works":["https://openalex.org/W3039671729","https://openalex.org/W7168415583","https://openalex.org/W3154412344","https://openalex.org/W4408490697","https://openalex.org/W4399198349","https://openalex.org/W4384811693","https://openalex.org/W3112027221","https://openalex.org/W4386794780","https://openalex.org/W7124118576","https://openalex.org/W4416945406"],"abstract_inverted_index":{"The":[0],"number":[1,12],"of":[2,13,43,67,94,161,177],"states":[3,111,125,162,207],"in":[4,10,20,56,63,80,90,140],"a":[5,60,96,101,141,151,174],"dynamic":[6],"process":[7],"is":[8,59,84],"exponential":[9,88],"the":[11,29,48,65,81,91,115,189],"objects,":[14],"making":[15],"reinforcement":[16],"learning":[17],"(RL)":[18],"difficult":[19],"complex,":[21],"multi-object":[22,68],"domains.":[23],"For":[24],"agents":[25,199],"to":[26,28,35,37,50,109,121,136,157,165,200,205,213,219],"scale":[27],"real":[30],"world,":[31],"they":[32],"will":[33,131],"need":[34],"react":[36],"and":[38,52,99,112,126,163,183,208],"reason":[39],"about":[40],"unseen":[41,110,124,206],"combinations":[42],"objects.":[44],"We":[45,134,193,210],"argue":[46],"that":[47,75,195,203],"ability":[49],"recognize":[51],"use":[53,211],"local":[54,78,116,178],"factorization":[55],"transition":[57],"dynamics":[58,97,104,129,155],"key":[61],"element":[62],"unlocking":[64],"power":[66],"reasoning.":[69],"To":[70],"this":[71,128],"end,":[72],"we":[73],"show":[74,194],"(1)":[76],"known":[77],"structure":[79,117],"environment":[82],"transitions":[83,168],"sufficient":[85],"for":[86,169,185],"an":[87,158,215,221],"reduction":[89],"sample":[92],"complexity":[93],"training":[95,191],"model,":[98],"(2)":[100],"locally":[102,153],"factored":[103,154],"model":[105,130,156],"provably":[106],"generalizes":[107],"out-of-distribution":[108,222],"actions.":[113,209],"Knowing":[114],"also":[118],"allows":[119,184],"us":[120],"predict":[122],"which":[123,227],"actions":[127,164],"generalize":[132,204],"to.":[133],"propose":[135],"leverage":[137],"these":[138],"observations":[139],"novel":[142],"Model-based":[143],"Counterfactual":[144],"Data":[145],"Augmentation":[146],"(MoCoDA)":[147],"framework.":[148],"MoCoDA":[149,171,196,212],"applies":[150],"learned":[152],"augmented":[159,190],"distribution":[160],"generate":[166],"counterfactual":[167],"RL.":[170],"works":[172],"with":[173],"broader":[175],"set":[176],"structures":[179],"than":[180],"prior":[181],"work":[182],"direct":[186],"control":[187],"over":[188],"distribution.":[192],"enables":[197],"RL":[198,217,230],"learn":[201],"policies":[202],"train":[214],"offline":[216,229],"agent":[218],"solve":[220],"robotics":[223],"manipulation":[224],"task":[225],"on":[226],"standard":[228],"algorithms":[231],"fail.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-03-03T00:00:00"}