{"id":"https://openalex.org/W4387687176","doi":"https://doi.org/10.5220/0012268200003543","title":"Improving Reward Estimation in Goal-Conditioned Imitation Learning with Counterfactual Data and Structural Causal Models","display_name":"Improving Reward Estimation in Goal-Conditioned Imitation Learning with Counterfactual Data and Structural Causal Models","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387687176","doi":"https://doi.org/10.5220/0012268200003543"},"language":"en","primary_location":{"id":"doi:10.5220/0012268200003543","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012268200003543","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.5220/0012268200003543","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070554929","display_name":"Mohamed Khalil Jabri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123702","display_name":"Laboratoire des Sciences et Techniques de l\u2019Information de la Communication et de la Connaissance","ror":"https://ror.org/0266kfd37","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I4210123702","https://openalex.org/I4210127572","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4210159245","https://openalex.org/I4405260085"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]},{"id":"https://openalex.org/I4210127572","display_name":"IMT Atlantique","ror":"https://ror.org/030hj3061","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210127572"]}],"countries":["AU","FR"],"is_corresponding":true,"raw_author_name":"Mohamed Jabri","raw_affiliation_strings":["Australian Institute for Machine Learning, Adelaide, Australia, --- Select a Country ---","IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France, --- Select a Country ---","IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","The University of Adelaide, Adelaide, Australia, --- Select a Country ---","University of Adelaide (Adelaide, South Australia, 5005 Australia - Australia)","CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)","Lab-STICC_RAMBO - Equipe Robot interaction, Ambient system, Machine learning, Behaviour, Optimization (France)"],"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, Adelaide, Australia, --- Select a Country ---","institution_ids":["https://openalex.org/I4210127558"]},{"raw_affiliation_string":"IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France, --- Select a Country ---","institution_ids":["https://openalex.org/I4210127572","https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I4210123702"]},{"raw_affiliation_string":"IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","institution_ids":[]},{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia, --- Select a Country ---","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"University of Adelaide (Adelaide, South Australia, 5005 Australia - Australia)","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)","institution_ids":[]},{"raw_affiliation_string":"Lab-STICC_RAMBO - Equipe Robot interaction, Ambient system, Machine learning, Behaviour, Optimization (France)","institution_ids":["https://openalex.org/I161929037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104533573","display_name":"Panagiotis Papadakis","orcid":"https://orcid.org/0000-0002-2193-8087"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210123702","display_name":"Laboratoire des Sciences et Techniques de l\u2019Information de la Communication et de la Connaissance","ror":"https://ror.org/0266kfd37","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I4210123702","https://openalex.org/I4210127572","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4210159245","https://openalex.org/I4405260085"]},{"id":"https://openalex.org/I4210127572","display_name":"IMT Atlantique","ror":"https://ror.org/030hj3061","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210127572"]},{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Panagiotis Papadakis","raw_affiliation_strings":["IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France, --- Select a Country ---","IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)","Lab-STICC_RAMBO - Equipe Robot interaction, Ambient system, Machine learning, Behaviour, Optimization (France)"],"affiliations":[{"raw_affiliation_string":"IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France, --- Select a Country ---","institution_ids":["https://openalex.org/I4210127572","https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I4210123702"]},{"raw_affiliation_string":"IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","institution_ids":[]},{"raw_affiliation_string":"CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)","institution_ids":[]},{"raw_affiliation_string":"Lab-STICC_RAMBO - Equipe Robot interaction, Ambient system, Machine learning, Behaviour, Optimization (France)","institution_ids":["https://openalex.org/I161929037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058061726","display_name":"Ehsan Abbasnejad","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]},{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ehsan Abbasnejad","raw_affiliation_strings":["Australian Institute for Machine Learning, Adelaide, Australia, --- Select a Country ---","IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","The University of Adelaide, Adelaide, Australia, --- Select a Country ---","CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)","University of Adelaide (Adelaide, South Australia, 5005 Australia - Australia)"],"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, Adelaide, Australia, --- Select a Country ---","institution_ids":["https://openalex.org/I4210127558"]},{"raw_affiliation_string":"IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","institution_ids":[]},{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia, --- Select a Country ---","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)","institution_ids":[]},{"raw_affiliation_string":"University of Adelaide (Adelaide, South Australia, 5005 Australia - Australia)","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088310451","display_name":"Gilles Coppin","orcid":"https://orcid.org/0000-0002-9193-425X"},"institutions":[{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]},{"id":"https://openalex.org/I4210127572","display_name":"IMT Atlantique","ror":"https://ror.org/030hj3061","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210127572"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210123702","display_name":"Laboratoire des Sciences et Techniques de l\u2019Information de la Communication et de la Connaissance","ror":"https://ror.org/0266kfd37","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I4210123702","https://openalex.org/I4210127572","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4210159245","https://openalex.org/I4405260085"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gilles Coppin","raw_affiliation_strings":["IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France, --- Select a Country ---","IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)"],"affiliations":[{"raw_affiliation_string":"IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France, --- Select a Country ---","institution_ids":["https://openalex.org/I4210127572","https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I4210123702"]},{"raw_affiliation_string":"IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","institution_ids":[]},{"raw_affiliation_string":"CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033588812","display_name":"Qinfeng Shi","orcid":"https://orcid.org/0000-0002-9126-2107"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Javen Shi","raw_affiliation_strings":["Australian Institute for Machine Learning, Adelaide, Australia, --- Select a Country ---","IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","The University of Adelaide, Adelaide, Australia, --- Select a Country ---","University of Adelaide (Adelaide, South Australia, 5005 Australia - Australia)","CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)"],"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, Adelaide, Australia, --- Select a Country ---","institution_ids":["https://openalex.org/I4210127558"]},{"raw_affiliation_string":"IRL CROSSING, CNRS, Adelaide, Australia, --- Select a Country ---","institution_ids":[]},{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia, --- Select a Country ---","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"University of Adelaide (Adelaide, South Australia, 5005 Australia - Australia)","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"CROSSING - FrenCh austRalian labOratory for humanS/autonomouS agents teamING (Adelaide - Australia)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070554929"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I4210123702","https://openalex.org/I4210127558","https://openalex.org/I4210127572","https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13791107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"329","last_page":"337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.982200026512146,"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":0.979200005531311,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9093122482299805},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6914833188056946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6433428525924683},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.500939130783081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49246320128440857},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.43687403202056885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40659022331237793},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27778875827789307},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13291653990745544},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12790408730506897}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9093122482299805},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6914833188056946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6433428525924683},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.500939130783081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49246320128440857},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.43687403202056885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40659022331237793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27778875827789307},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13291653990745544},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12790408730506897},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0012268200003543","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012268200003543","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04238529v1","is_oa":true,"landing_page_url":"https://imt-atlantique.hal.science/hal-04238529/document","pdf_url":"https://imt-atlantique.hal.science/hal-04238529v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://icinco.scitevents.org","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.5220/0012268200003543","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012268200003543","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2155027007","https://openalex.org/W2174803659","https://openalex.org/W2257979135","https://openalex.org/W2963277051","https://openalex.org/W2963864421","https://openalex.org/W2964201867","https://openalex.org/W2970377754","https://openalex.org/W2980897231","https://openalex.org/W3035603281","https://openalex.org/W4214717370","https://openalex.org/W4251121616","https://openalex.org/W4283772362","https://openalex.org/W4288019212","https://openalex.org/W4293872189","https://openalex.org/W4294786244","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W4301372783"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W3201448254"],"abstract_inverted_index":{"International":[0],"audience":[1]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}