{"id":"https://openalex.org/W4297982141","doi":null,"title":"Batch, Off-policy and Model-Free Apprenticeship Learning","display_name":"Batch, Off-policy and Model-Free Apprenticeship Learning","publication_year":2011,"publication_date":"2011-06-16","ids":{"openalex":"https://openalex.org/W4297982141"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.36","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ewrl.files.wordpress.com/2011/08/ewrl2011_submission_18.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5000665687","display_name":"Edouard Klein","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edouard Klein","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal","Machine Learning and Computational Biology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal","institution_ids":[]},{"raw_affiliation_string":"Machine Learning and Computational Biology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":"https://orcid.org/0009-0002-7888-8233","observed_orcids":["https://orcid.org/0009-0002-7888-8233"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X","observed_orcids":["https://orcid.org/0000-0002-5386-465X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44747125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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/T12072","display_name":"Machine Learning and Algorithms","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/imitation-learning","display_name":"imitation learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/inverse-reinforcement-learning","display_name":"inverse reinforcement learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.9480000138282776},{"id":"https://openalex.org/keywords/batch-learning","display_name":"batch learning","score":0.6970000267028809},{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.9710000157356262},{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.8560000061988831},{"id":"https://openalex.org/keywords/reward-function-learning","display_name":"reward function learning","score":0.6610000133514404},{"id":"https://openalex.org/keywords/expert-trajectories","display_name":"expert trajectories","score":0.4560000002384186}],"concepts":[{"id":"https://openalex.org/C107806365","wikidata":"https://www.wikidata.org/wiki/Q253567","display_name":"Apprenticeship","level":2,"score":0.773077666759491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6145229935646057},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.36","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ewrl.files.wordpress.com/2011/08/ewrl2011_submission_18.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.357.9385","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.357.9385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/~bradknox/IJCAI-ALIHT11-papers/aliht2011_submission_9.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.4788","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.4788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.metz.supelec.fr//metz/personnel/geist_mat/pdfs/supelec726.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00596370v1","doi":null,"is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00596370","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IJCAI Workshop on Agents Learning Interactively from Human Teachers (ALIHT 2011), Jun 2011, Barcelona, Spain. 6 p","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-00660623v1","doi":null,"is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00660623","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EWRL 2011, Sep 2011, Athens, Greece. pp.1-12","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3087352516","https://openalex.org/W2923483157","https://openalex.org/W1999874108","https://openalex.org/W3215946589","https://openalex.org/W7099390080","https://openalex.org/W2350279505","https://openalex.org/W2102847492","https://openalex.org/W2103235543","https://openalex.org/W2148051740","https://openalex.org/W2113023245"],"abstract_inverted_index":{"Abstract.":[0],"This":[1,116],"paper":[2],"addresses":[3],"the":[4,31,34,44,55,64,86],"problem":[5],"of":[6,66],"apprenticeship":[7,119],"learning,":[8],"that":[9,33,54],"is":[10,24,58,72],"learning":[11,27,43,120],"control":[12],"policies":[13],"from":[14,47],"demonstration":[15],"by":[16],"an":[17],"expert.":[18],"An":[19],"ef-ficient":[20],"framework":[21],"for":[22,85,97],"it":[23],"inverse":[25],"reinforcement":[26],"(IRL).":[28],"Based":[29],"on":[30,63],"assumption":[32],"expert":[35,87],"maximizes":[36],"a":[37,94,105,122],"utility":[38],"function,":[39],"IRL":[40,51],"aims":[41],"at":[42,92],"underlying":[45],"reward":[46,56],"example":[48],"trajectories.":[49],"Many":[50],"al-gorithms":[52],"assume":[53],"function":[57],"linearly":[59],"parameterized":[60],"and":[61,124],"rely":[62],"computation":[65],"some":[67],"associated":[68],"feature":[69,114],"expectations,":[70],"which":[71],"done":[73],"through":[74],"Monte":[75],"Carlo":[76],"simulation.":[77],"However,":[78],"this":[79,101],"assumes":[80],"to":[81,111,121],"have":[82],"full":[83],"trajectories":[84],"policy":[88],"as":[89,91],"well":[90],"least":[93],"generative":[95],"model":[96],"intermediate":[98],"policies.":[99],"In":[100],"paper,":[102],"we":[103],"introduce":[104],"temporal":[106],"differ-ence":[107],"method,":[108],"namely":[109],"LSTD-\u00b5,":[110],"compute":[112],"these":[113],"expectations.":[115],"allows":[117],"extending":[118],"batch":[123],"off-policy":[125],"setting.":[126],"1":[127]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2025-10-10T00:00:00"}