{"id":"https://openalex.org/W7124284875","doi":"https://doi.org/10.65109/mgkh7405","title":"Robust Learning from Observation with Model Misspecification","display_name":"Robust Learning from Observation with Model Misspecification","publication_year":2022,"publication_date":"2022-05-09","ids":{"openalex":"https://openalex.org/W7124284875","doi":"https://doi.org/10.65109/mgkh7405"},"language":"en","primary_location":{"id":"doi:10.65109/mgkh7405","doi":"https://doi.org/10.65109/mgkh7405","is_oa":false,"landing_page_url":"https://doi.org/10.65109/mgkh7405","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","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/2202.06003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083025579","display_name":"Luca Viano","orcid":"https://orcid.org/0009-0002-1028-6893","observed_orcids":["https://orcid.org/0009-0002-1028-6893"]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca Viano","raw_affiliation_strings":["LIONS, EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIONS, EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014676064","display_name":"Yu\u2010Ting Huang","orcid":"https://orcid.org/0000-0002-9773-2122","observed_orcids":["https://orcid.org/0000-0002-9773-2122"]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yu-Ting Huang","raw_affiliation_strings":["EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090876613","display_name":"Parameswaran Kamalaruban","orcid":"https://orcid.org/0000-0002-2929-7886","observed_orcids":["https://orcid.org/0000-0002-2929-7886"]},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Parameswaran Kamalaruban","raw_affiliation_strings":["The Alan Turing Institute, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618980","display_name":"Craig Innes","orcid":"https://orcid.org/0000-0002-6329-4136","observed_orcids":["https://orcid.org/0000-0002-6329-4136"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Innes","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123048172","display_name":"Subramanian Ramamoorthy","orcid":"https://orcid.org/0000-0002-6300-5103","observed_orcids":["https://orcid.org/0000-0002-6300-5103"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Subramanian Ramamoorthy","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042278493","display_name":"Adrian Weller","orcid":"https://orcid.org/0000-0003-1915-7158","observed_orcids":["https://orcid.org/0000-0003-1915-7158"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adrian Weller","raw_affiliation_strings":["University of Cambridge & The Alan Turing Institute, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge & The Alan Turing Institute, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210128584"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6286,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.68523785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1337","last_page":"1345"},"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/T10653","display_name":"Robot Manipulation and Learning","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/imitation-learning","display_name":"imitation learning","score":0.9710000157356262},{"id":"https://openalex.org/keywords/model-misspecification","display_name":"model misspecification","score":0.871999979019165},{"id":"https://openalex.org/keywords/robust-reinforcement-learning","display_name":"robust reinforcement learning","score":0.8379999995231628},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.6779999732971191},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.7699999809265137},{"id":"https://openalex.org/keywords/generative-adversarial-imitation-learning","display_name":"generative adversarial imitation learning","score":0.8610000014305115},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.7429999709129333},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426999807357788},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6266999840736389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6225000023841858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5723000168800354},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5472999811172485},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.65109/mgkh7405","doi":"https://doi.org/10.65109/mgkh7405","is_oa":false,"landing_page_url":"https://doi.org/10.65109/mgkh7405","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2202.06003","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.06003","pdf_url":"https://arxiv.org/pdf/2202.06003","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":"pmh:oai:pure.ed.ac.uk:openaire/6758d45e-d369-4370-ba37-d92f4d7bd84c","doi":null,"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/6758d45e-d369-4370-ba37-d92f4d7bd84c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Viano, L, Huang, Y-T, Kamalaruban, P, Innes, C, Ramamoorthy, S & Weller, A 2022, Robust learning from observation with model misspecification. in C Pelachaud, M E Taylor, P Faliszewski & V Mascardi (eds), Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022). pp. 1337-1345, 21st International Conference on Autonomous Agents and Multiagent Systems , Auckland, New Zealand, 9/05/22. https://doi.org/10.5555/3535850.3535999","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.2202.06003","doi":"https://doi.org/10.48550/arxiv.2202.06003","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2202.06003","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:2202.06003","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.06003","pdf_url":"https://arxiv.org/pdf/2202.06003","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/G1890506141","display_name":"UKRI Trustworthy Autonomous Systems Node in Governance and Regulation","funder_award_id":"EP/V026607/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3136057049","display_name":null,"funder_award_id":"2020-2024","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G4683617588","display_name":null,"funder_award_id":"EP/V026607/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G7196478567","display_name":"Advancing Probabilistic Machine Learning to Deliver Safer, More Efficient, and Predictable Air Traffic Control","funder_award_id":"EP/V056522/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320313467","display_name":"Alan Turing Institute","ror":"https://ror.org/035dkdb55"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320319993","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124284875.pdf","grobid_xml":"https://content.openalex.org/works/W7124284875.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2462906003","https://openalex.org/W2736601468","https://openalex.org/W2884247313","https://openalex.org/W3016047885","https://openalex.org/W3037207827"],"related_works":["https://openalex.org/W7052617256","https://openalex.org/W4416161703","https://openalex.org/W3082790045","https://openalex.org/W4387561392","https://openalex.org/W6968850656","https://openalex.org/W2995626170","https://openalex.org/W4393147296","https://openalex.org/W4398795053","https://openalex.org/W4283315089","https://openalex.org/W7162442972"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,129,152],"(IL)":[2],"is":[3,18,49,78,88],"a":[4,45,55,81,164],"popular":[5],"paradigm":[6],"for":[7],"training":[8,110],"policies":[9,170],"in":[10,43,80,197,204],"robotic":[11],"systems":[12],"when":[13],"specifying":[14],"the":[15,22,29,34,40,64,71,74,92,97,105,109,113,120,137,142,149,176,192,200,205],"reward":[16],"function":[17],"difficult.":[19],"However,":[20],"despite":[21],"success":[23],"of":[24,115,119,199],"IL":[25,122,166,195],"algorithms,":[26],"they":[27],"impose":[28],"somewhat":[30],"unrealistic":[31],"requirement":[32],"that":[33,171,188],"expert":[35,61,139],"demonstrations":[36,62,116],"must":[37],"come":[38],"from":[39,63,91,148],"same":[41],"domain":[42],"which":[44],"new":[46],"imitator":[47],"policy":[48,77],"to":[50,70,104,135,168,175],"be":[51],"learned.":[52],"We":[53],"consider":[54],"practical":[56],"setting,":[57],"where":[58],"(i)":[59],"state-only":[60,132,194],"real":[65,93,106,177,206],"(deployment)":[66],"environment":[67,84,107,178,207],"are":[68],"given":[69],"learner,":[72],"(ii)":[73],"imitation":[75,128,160],"learner":[76,98],"trained":[79],"simulation":[82],"(training)":[83],"whose":[85],"transition":[86],"dynamics":[87],"slightly":[89],"different":[90,212],"environment,":[94],"and":[95,130,155,208],"(iii)":[96],"does":[99],"not":[100],"have":[101],"any":[102],"access":[103],"during":[108],"phase":[111],"beyond":[112],"batch":[114],"given.":[117],"Most":[118],"current":[121],"methods,":[123],"such":[124],"as":[125],"generative":[126],"adversarial":[127,159],"its":[131],"variants,":[133],"fail":[134],"imitate":[136],"optimal":[138],"behavior":[140],"under":[141,211],"above":[143],"setting.":[144],"By":[145],"leveraging":[146],"insights":[147],"Robust":[150],"reinforcement":[151],"(RL)":[153],"literature":[154],"building":[156],"on":[157,185],"recent":[158],"approaches,":[161],"we":[162,182],"propose":[163],"robust":[165,209],"algorithm":[167],"learn":[169],"can":[172],"effectively":[173],"transfer":[174,202],"without":[179],"fine-tuning.":[180],"Furthermore,":[181],"empirically":[183],"demonstrate":[184],"continuous-control":[186],"benchmarks":[187],"our":[189],"method":[190,196],"outperforms":[191],"state-of-the-art":[193],"terms":[198],"zero-shot":[201],"performance":[203,210],"testing":[213],"conditions.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-01-16T00:00:00"}