{"id":"https://openalex.org/W2953259115","doi":"https://doi.org/10.1007/s10994-018-5730-4","title":"Inverse reinforcement learning from summary data","display_name":"Inverse reinforcement learning from summary data","publication_year":2018,"publication_date":"2018-06-27","ids":{"openalex":"https://openalex.org/W2953259115","doi":"https://doi.org/10.1007/s10994-018-5730-4","mag":"2953259115"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-018-5730-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-018-5730-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5730-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5730-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Antti Kangasr\u00e4\u00e4si\u00f6","orcid":"https://orcid.org/0000-0001-6072-7787"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Antti Kangasr\u00e4\u00e4si\u00f6","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0001-6072-7787","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":null,"display_name":"Samuel Kaski","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Samuel Kaski","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.3689,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.7398895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"107","issue":"8-10","first_page":"1517","last_page":"1535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7103999853134155,"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":0.7103999853134155,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.035100001841783524,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.02759999968111515,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6922000050544739},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6913999915122986},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.505299985408783},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4722999930381775},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.34630000591278076},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.33559998869895935}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6922000050544739},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6913999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6854000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6146000027656555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5751000046730042},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.34630000591278076},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C89106044","wikidata":"https://www.wikidata.org/wiki/Q45284","display_name":"Likelihood function","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10994-018-5730-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-018-5730-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5730-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/8114b2db-5eff-4efa-bd83-131e1c21d3f3","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/8114b2db-5eff-4efa-bd83-131e1c21d3f3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kangasr\u00e4\u00e4si\u00f6, A & Kaski, S 2018, 'Inverse reinforcement learning from summary data', Machine Learning, vol. 107, no. 8-10, pp. 1517\u20131535. https://doi.org/10.1007/s10994-018-5730-4","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:1703.09700","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.09700","pdf_url":"https://arxiv.org/pdf/1703.09700","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,"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"}],"best_oa_location":{"id":"doi:10.1007/s10994-018-5730-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-018-5730-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5730-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4249896723","display_name":null,"funder_award_id":"251170","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G5498917553","display_name":null,"funder_award_id":"294238","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G7966353708","display_name":null,"funder_award_id":"292334","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953259115.pdf","grobid_xml":"https://content.openalex.org/works/W2953259115.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W52822972","https://openalex.org/W1480330138","https://openalex.org/W1502641836","https://openalex.org/W1502922572","https://openalex.org/W1566073559","https://openalex.org/W1567876833","https://openalex.org/W1591675293","https://openalex.org/W1607751291","https://openalex.org/W1677005304","https://openalex.org/W1815701967","https://openalex.org/W1846353404","https://openalex.org/W1999874108","https://openalex.org/W2011164895","https://openalex.org/W2032616735","https://openalex.org/W2062525454","https://openalex.org/W2097714468","https://openalex.org/W2098774185","https://openalex.org/W2099201756","https://openalex.org/W2100401322","https://openalex.org/W2101821104","https://openalex.org/W2109168899","https://openalex.org/W2116442740","https://openalex.org/W2116774898","https://openalex.org/W2133068870","https://openalex.org/W2134491302","https://openalex.org/W2144592607","https://openalex.org/W2146354794","https://openalex.org/W2151204864","https://openalex.org/W2169498096","https://openalex.org/W2187006281","https://openalex.org/W2338865890","https://openalex.org/W2396863940","https://openalex.org/W2397891592","https://openalex.org/W2409689189","https://openalex.org/W2534708821","https://openalex.org/W2606862087","https://openalex.org/W2911273949","https://openalex.org/W4232512588"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2019-06-27T00:00:00"}