{"id":"https://openalex.org/W3042593733","doi":"https://doi.org/10.48550/arxiv.2007.07812","title":"Inverse Reinforcement Learning from a Gradient-based Learner","display_name":"Inverse Reinforcement Learning from a Gradient-based Learner","publication_year":2020,"publication_date":"2020-07-15","ids":{"openalex":"https://openalex.org/W3042593733","doi":"https://doi.org/10.48550/arxiv.2007.07812","mag":"3042593733"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2007.07812","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.07812","pdf_url":"https://arxiv.org/pdf/2007.07812","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":null,"license_id":null,"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/2007.07812","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048076721","display_name":"Giorgia Ramponi","orcid":"https://orcid.org/0000-0002-3076-5448","observed_orcids":["https://orcid.org/0000-0002-3076-5448"]},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ramponi, Giorgia","raw_affiliation_strings":["Politecnico Di Milano","Polytechnic University of Milan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico Di Milano","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Polytechnic University of Milan","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088578493","display_name":"Gianluca Drappo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Drappo, Gianluca","raw_affiliation_strings":["Politecnico Di Milano","Polytechnic University of Milan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico Di Milano","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Polytechnic University of Milan","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076","observed_orcids":["https://orcid.org/0000-0002-6322-1076"]},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Restelli, Marcello","raw_affiliation_strings":["Politecnico Di Milano","Polytechnic University of Milan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico Di Milano","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Polytechnic University of Milan","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"2458","last_page":"2468"},"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inverse-reinforcement-learning","display_name":"inverse reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/reward-function-inference","display_name":"reward function inference","score":0.7519999742507935},{"id":"https://openalex.org/keywords/gradient-based-learning","display_name":"gradient-based learning","score":0.7409999966621399},{"id":"https://openalex.org/keywords/learning-trajectories","display_name":"learning trajectories","score":0.6230000257492065},{"id":"https://openalex.org/keywords/expert-demonstrations","display_name":"expert demonstrations","score":0.453000009059906},{"id":"https://openalex.org/keywords/mujoco","display_name":"MuJoCo","score":0.6399999856948853},{"id":"https://openalex.org/keywords/grid-world","display_name":"grid world","score":0.972000002861023}],"concepts":[{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5785239934921265},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5753766894340515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5327140688896179},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5044184923171997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3762441575527191},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2129635512828827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17271706461906433},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.060202598571777344},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2007.07812","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.07812","pdf_url":"https://arxiv.org/pdf/2007.07812","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:re.public.polimi.it:11311/1167115","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1167115","pdf_url":"http://hdl.handle.net/11311/1167115","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2007.07812","doi":"https://doi.org/10.48550/arxiv.2007.07812","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.07812","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:3106008061","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2020/file/19aa6c6fb4ba9fcf39e893ff1fd5b5bd-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.07812","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.07812","pdf_url":"https://arxiv.org/pdf/2007.07812","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":null,"license_id":null,"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/G15967578","display_name":null,"funder_award_id":"PRIN_2017","funder_id":"https://openalex.org/F4320321873","funder_display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca"}],"funders":[{"id":"https://openalex.org/F4320321873","display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","ror":"https://ror.org/0166hxq48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3042593733.pdf","grobid_xml":"https://content.openalex.org/works/W3042593733.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1540764732","https://openalex.org/W1986014385","https://openalex.org/W1988181581","https://openalex.org/W1999874108","https://openalex.org/W2000671978","https://openalex.org/W2061562262","https://openalex.org/W2097826646","https://openalex.org/W2098774185","https://openalex.org/W2112964839","https://openalex.org/W2115450697","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2125612430","https://openalex.org/W2127107099","https://openalex.org/W2137966130","https://openalex.org/W2144446635","https://openalex.org/W2150200785","https://openalex.org/W2155027007","https://openalex.org/W2169209873","https://openalex.org/W2312609093","https://openalex.org/W2398964619","https://openalex.org/W2562989799","https://openalex.org/W2604382266","https://openalex.org/W2609650878","https://openalex.org/W2736601468","https://openalex.org/W2753088790","https://openalex.org/W2781726626","https://openalex.org/W2794908222","https://openalex.org/W2939047085","https://openalex.org/W2945995507","https://openalex.org/W2946258294","https://openalex.org/W2953671406","https://openalex.org/W2962940757","https://openalex.org/W2962943921","https://openalex.org/W2963965884","https://openalex.org/W2964263543","https://openalex.org/W2964912293","https://openalex.org/W3037207827"],"related_works":["https://openalex.org/W2116442740","https://openalex.org/W2562989799","https://openalex.org/W2738629594","https://openalex.org/W2156163138","https://openalex.org/W2741991979","https://openalex.org/W4403995540","https://openalex.org/W1999874108","https://openalex.org/W3088674748","https://openalex.org/W2753088790","https://openalex.org/W7099390080"],"abstract_inverted_index":{"Inverse":[0],"Reinforcement":[1],"Learning":[2],"addresses":[3],"the":[4,24,50,55,76,79,88,99,128,137,143],"problem":[5],"of":[6,33,66,111],"inferring":[7],"an":[8,61],"expert's":[9,25],"reward":[10,56],"function":[11,57],"from":[12],"demonstrations.":[13],"However,":[14],"in":[15,48,130],"many":[16],"applications,":[17],"we":[18,29,40,92,104,117,126],"not":[19],"only":[20,105],"have":[21,106],"access":[22,107],"to":[23,53,96,108],"near-optimal":[26],"behavior,":[27],"but":[28],"also":[30],"observe":[31],"part":[32],"her":[34,84],"learning":[35,112],"process.":[36],"In":[37],"this":[38,46],"paper,":[39],"propose":[41],"a":[42,64,109,131],"new":[43],"algorithm":[44],"for":[45],"setting,":[47],"which":[49],"goal":[51],"is":[52,73,82],"recover":[54],"being":[58],"optimized":[59],"by":[60],"agent,":[62],"given":[63],"sequence":[65],"policies":[67],"produced":[68],"during":[69],"learning.":[70],"Our":[71],"approach":[72,129],"based":[74],"on":[75,136],"assumption":[77],"that":[78],"observed":[80],"agent":[81],"updating":[83],"policy":[85],"parameters":[86],"along":[87],"gradient":[89],"direction.":[90],"Then":[91],"extend":[93],"our":[94,122],"method":[95],"deal":[97],"with":[98,142],"more":[100],"realistic":[101],"scenario":[102],"where":[103],"dataset":[110],"trajectories.":[113],"For":[114],"both":[115],"settings,":[116],"provide":[118],"theoretical":[119],"insights":[120],"into":[121],"algorithms'":[123],"performance.":[124],"Finally,":[125],"evaluate":[127],"simulated":[132],"GridWorld":[133],"environment":[134],"and":[135],"MuJoCo":[138],"environments,":[139],"comparing":[140],"it":[141],"state-of-the-art":[144],"baseline.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-07-23T00:00:00"}