{"id":"https://openalex.org/W2804020409","doi":"https://doi.org/10.48550/arxiv.1805.07914","title":"Imitating Latent Policies from Observation","display_name":"Imitating Latent Policies from Observation","publication_year":2018,"publication_date":"2018-05-21","ids":{"openalex":"https://openalex.org/W2804020409","doi":"https://doi.org/10.48550/arxiv.1805.07914","mag":"2804020409"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1805.07914","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.07914","pdf_url":"https://arxiv.org/pdf/1805.07914","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/1805.07914","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112414179","display_name":"Ashley D. Edwards","orcid":"https://orcid.org/0009-0007-1129-5114","observed_orcids":["https://orcid.org/0009-0007-1129-5114"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edwards, Ashley D.","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058921365","display_name":"Himanshu Sahni","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sahni, Himanshu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084125996","display_name":"Yannick Schroecker","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schroecker, Yannick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091212723","display_name":"Charles Lee Isbell","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Isbell, Charles L.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":88,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1755","last_page":"1763"},"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/T10906","display_name":"AI-based Problem Solving and Planning","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":0.9459999799728394},{"id":"https://openalex.org/keywords/platform-games","display_name":"platform games","score":0.5130000114440918},{"id":"https://openalex.org/keywords/control-environment","display_name":"control environment","score":0.39100000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785455584526062},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.643357515335083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.573782205581665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690368413925171},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5468593835830688},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5381328463554382},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07283997535705566},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1805.07914","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.07914","pdf_url":"https://arxiv.org/pdf/1805.07914","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":"doi:10.48550/arxiv.1805.07914","doi":"https://doi.org/10.48550/arxiv.1805.07914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.07914","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":"Preprint"},{"id":"mag:2963511511","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v97/edwards19a/edwards19a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.07914","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.07914","pdf_url":"https://arxiv.org/pdf/1805.07914","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2804020409.pdf","grobid_xml":"https://content.openalex.org/works/W2804020409.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1540685400","https://openalex.org/W1994585255","https://openalex.org/W1999874108","https://openalex.org/W2053910308","https://openalex.org/W2061562262","https://openalex.org/W2118688707","https://openalex.org/W2181849516","https://openalex.org/W2257979135","https://openalex.org/W2434014514","https://openalex.org/W2434741482","https://openalex.org/W2583137229","https://openalex.org/W2591957724","https://openalex.org/W2606047872","https://openalex.org/W2750875954","https://openalex.org/W2756826236","https://openalex.org/W2768959015","https://openalex.org/W2776202271","https://openalex.org/W2786487443","https://openalex.org/W2795158776","https://openalex.org/W2796054047","https://openalex.org/W2802726207","https://openalex.org/W2806029110","https://openalex.org/W2884247313","https://openalex.org/W2903181768","https://openalex.org/W2949536664","https://openalex.org/W2951961145","https://openalex.org/W2962715211","https://openalex.org/W2963221965","https://openalex.org/W2963328631","https://openalex.org/W2963802910","https://openalex.org/W2964127152","https://openalex.org/W6960125083"],"related_works":["https://openalex.org/W4391186814","https://openalex.org/W3212871970","https://openalex.org/W2786663522","https://openalex.org/W2434014514","https://openalex.org/W4387294502","https://openalex.org/W4381250507","https://openalex.org/W7097368714","https://openalex.org/W7099101307","https://openalex.org/W7134058253","https://openalex.org/W4283462717"],"abstract_inverted_index":{"In":[0],"this":[1,66,107],"paper,":[2],"we":[3],"describe":[4],"a":[5,21,47,55,93],"novel":[6],"approach":[7,87],"to":[8,53],"imitation":[9],"learning":[10],"that":[11,23,45,65,98],"infers":[12],"latent":[13,29,59],"policies":[14],"directly":[15],"from":[16],"state":[17],"observations.":[18],"We":[19,38,63,84],"introduce":[20],"method":[22],"characterizes":[24],"the":[25,58,74],"causal":[26],"effects":[27],"of":[28,50],"actions":[30,81],"on":[31],"observations":[32],"while":[33],"simultaneously":[34],"predicting":[35],"their":[36],"likelihood.":[37],"then":[39],"outline":[40],"an":[41],"action":[42],"alignment":[43],"procedure":[44],"leverages":[46],"small":[48],"amount":[49],"environment":[51],"interactions":[52],"determine":[54],"mapping":[56],"between":[57],"and":[60,92,96],"real-world":[61],"actions.":[62],"show":[64],"corrected":[67],"labeling":[68],"can":[69],"be":[70],"used":[71],"for":[72,106],"imitating":[73],"observed":[75],"behavior,":[76],"even":[77],"though":[78],"no":[79],"expert":[80],"are":[82],"given.":[83],"evaluate":[85],"our":[86],"within":[88],"classic":[89],"control":[90],"environments":[91],"platform":[94],"game":[95],"demonstrate":[97],"it":[99],"performs":[100],"better":[101],"than":[102],"standard":[103],"approaches.":[104],"Code":[105],"work":[108],"is":[109],"available":[110],"at":[111],"https://github.com/ashedwards/ILPO.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-06-01T00:00:00"}