{"id":"https://openalex.org/W4392019348","doi":"https://doi.org/10.48550/arxiv.2402.13037","title":"Align Your Intents: Offline Imitation Learning via Optimal Transport","display_name":"Align Your Intents: Offline Imitation Learning via Optimal Transport","publication_year":2024,"publication_date":"2024-02-20","ids":{"openalex":"https://openalex.org/W4392019348","doi":"https://doi.org/10.48550/arxiv.2402.13037"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.13037","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13037","pdf_url":"https://arxiv.org/pdf/2402.13037","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","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/2402.13037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093975888","display_name":"Maksim Bobrin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Bobrin, Maksim","raw_affiliation_strings":["Skolkovo Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034143409","display_name":"Nazar Buzun","orcid":"https://orcid.org/0000-0002-4649-2827","observed_orcids":["https://orcid.org/0000-0002-4649-2827"]},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"id":"https://openalex.org/I4392021246","display_name":"AIRI - Artificial Intelligence Research Institute","ror":"https://ror.org/014a87f14","country_code":"RU","type":"nonprofit","lineage":["https://openalex.org/I4392021246"]}],"countries":["ES","RU"],"is_corresponding":false,"raw_author_name":"Buzun, Nazar","raw_affiliation_strings":["Artificial Intelligence Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute","institution_ids":["https://openalex.org/I4210131846","https://openalex.org/I4392021246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050896803","display_name":"Dmitrii Krylov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krylov, Dmitrii","raw_affiliation_strings":["University of California , Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031517308","display_name":"Dmitry V. Dylov","orcid":"https://orcid.org/0000-0003-2251-3221","observed_orcids":["https://orcid.org/0000-0003-2251-3221"]},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dylov, Dmitry V.","raw_affiliation_strings":["Skolkovo Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/offline-imitation-learning","display_name":"offline imitation learning","score":0.9800000190734863},{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.9290000200271606},{"id":"https://openalex.org/keywords/optimal-transport","display_name":"optimal transport","score":0.8360000252723694},{"id":"https://openalex.org/keywords/intrinsic-rewards","display_name":"intrinsic rewards","score":0.7820000052452087},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.8100000023841858},{"id":"https://openalex.org/keywords/d4rl-benchmark","display_name":"D4RL benchmark","score":0.7120000123977661},{"id":"https://openalex.org/keywords/trajectory-distance","display_name":"trajectory distance","score":0.4309999942779541}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6803045272827148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5011541843414307},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3615058660507202},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34930992126464844},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.22384944558143616}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.13037","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13037","pdf_url":"https://arxiv.org/pdf/2402.13037","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.13037","doi":"https://doi.org/10.48550/arxiv.2402.13037","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.13037","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.13037","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13037","pdf_url":"https://arxiv.org/pdf/2402.13037","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392019348.pdf","grobid_xml":"https://content.openalex.org/works/W4392019348.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2785672818","https://openalex.org/W2788741142","https://openalex.org/W2884247313","https://openalex.org/W2904339729","https://openalex.org/W2952451928","https://openalex.org/W2953326529","https://openalex.org/W2975999915","https://openalex.org/W2976902166","https://openalex.org/W2995709298","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3097907450","https://openalex.org/W3108231325","https://openalex.org/W3202850137","https://openalex.org/W4221157780","https://openalex.org/W4226072009","https://openalex.org/W4291960900","https://openalex.org/W4309125149","https://openalex.org/W4361020557","https://openalex.org/W4385430582","https://openalex.org/W4387687244","https://openalex.org/W4388184352","https://openalex.org/W4388184456","https://openalex.org/W4401414432","https://openalex.org/W7133205423","https://openalex.org/W7133228304"],"related_works":["https://openalex.org/W4361020557","https://openalex.org/W7162470533","https://openalex.org/W4391631813","https://openalex.org/W4415795525","https://openalex.org/W4387355780","https://openalex.org/W7106169679","https://openalex.org/W4411143217","https://openalex.org/W4324266479","https://openalex.org/W4400719260","https://openalex.org/W4403444501"],"abstract_inverted_index":{"Offline":[0],"Reinforcement":[1],"Learning":[2,77],"(RL)":[3],"addresses":[4],"the":[5,20,33,54,60,63,98,113,116,135,147],"problem":[6],"of":[7,65,85,90,137],"sequential":[8],"decision-making":[9],"by":[10,142],"learning":[11,128],"optimal":[12,109],"policy":[13],"through":[14],"pre-collected":[15],"data,":[16],"without":[17],"interacting":[18],"with":[19],"environment.":[21],"As":[22],"yet,":[23],"it":[24,37,42],"has":[25],"remained":[26],"somewhat":[27],"impractical,":[28],"because":[29],"one":[30],"rarely":[31],"knows":[32],"reward":[34,106,144],"explicitly":[35],"and":[36,115,133],"is":[38],"hard":[39],"to":[40],"distill":[41],"retrospectively.":[43],"Here,":[44],"we":[45,81,103],"show":[46],"that":[47,92,121],"an":[48],"imitating":[49],"agent":[50],"can":[51],"still":[52],"learn":[53],"desired":[55],"behavior":[56],"merely":[57],"from":[58],"observing":[59],"expert,":[61],"despite":[62],"absence":[64],"explicit":[66],"rewards":[67],"or":[68],"action":[69],"labels.":[70],"In":[71],"our":[72],"method,":[73],"AILOT":[74,122],"(Aligned":[75],"Imitation":[76],"via":[78,108],"Optimal":[79],"Transport),":[80],"involve":[82],"special":[83],"representation":[84],"states":[86],"in":[87,146],"a":[88],"form":[89],"intents":[91],"incorporate":[93],"pairwise":[94],"spatial":[95],"distances":[96],"within":[97],"data.":[99],"Given":[100],"such":[101],"representations,":[102],"define":[104],"intrinsic":[105],"function":[107],"transport":[110],"distance":[111],"between":[112],"expert's":[114],"agent's":[117],"trajectories.":[118],"We":[119],"report":[120],"outperforms":[123],"state-of-the":[124],"art":[125],"offline":[126,139],"imitation":[127],"algorithms":[129,141],"on":[130],"D4RL":[131],"benchmarks":[132],"improves":[134],"performance":[136],"other":[138],"RL":[140],"dense":[143],"relabelling":[145],"sparse-reward":[148],"tasks.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2024-02-22T00:00:00"}