{"id":"https://openalex.org/W3167305842","doi":"https://doi.org/10.1109/icra48506.2021.9561119","title":"Learning from Demonstration without Demonstrations","display_name":"Learning from Demonstration without Demonstrations","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3167305842","doi":"https://doi.org/10.1109/icra48506.2021.9561119","mag":"3167305842"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.09203","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022111646","display_name":"Tom Blau","orcid":"https://orcid.org/0000-0001-5148-5640"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Tom Blau","raw_affiliation_strings":["CSIRO, Australia","School of Computer Science, The University of Sydney, Australia","CSIRO, "],"affiliations":[{"raw_affiliation_string":"CSIRO, Australia","institution_ids":["https://openalex.org/I1292875679"]},{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"CSIRO, ","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038103937","display_name":"Philippe Morere","orcid":"https://orcid.org/0000-0001-6035-1724"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Philippe Morere","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067160257","display_name":"Gilad Francis","orcid":"https://orcid.org/0000-0001-7910-8556"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gilad Francis","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022111646"],"corresponding_institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06993214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4116","last_page":"4122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9887999892234802,"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/leverage","display_name":"Leverage (statistics)","score":0.7790548801422119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.745985209941864},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7054480314254761},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6514386534690857},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6284813284873962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5978571176528931},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5787434577941895},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5274515151977539},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5155056118965149},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.4870319962501526},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.479621022939682},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4179501533508301},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.24751463532447815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10901039838790894},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0850328803062439}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7790548801422119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745985209941864},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7054480314254761},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6514386534690857},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6284813284873962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5978571176528931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5787434577941895},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5274515151977539},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5155056118965149},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.4870319962501526},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.479621022939682},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4179501533508301},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.24751463532447815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10901039838790894},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0850328803062439},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.09203","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.09203","pdf_url":"https://arxiv.org/pdf/2106.09203","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:3167305842","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2106.09203","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.09203","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.09203","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.09203","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.09203","pdf_url":"https://arxiv.org/pdf/2106.09203","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167305842.pdf","grobid_xml":"https://content.openalex.org/works/W3167305842.grobid-xml"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W131069610","https://openalex.org/W779494576","https://openalex.org/W1480053368","https://openalex.org/W1533861849","https://openalex.org/W1771410628","https://openalex.org/W1971086298","https://openalex.org/W1986014385","https://openalex.org/W1994923984","https://openalex.org/W2000359213","https://openalex.org/W2036016432","https://openalex.org/W2051228319","https://openalex.org/W2059355691","https://openalex.org/W2128990851","https://openalex.org/W2136310975","https://openalex.org/W2141664020","https://openalex.org/W2143826757","https://openalex.org/W2144744117","https://openalex.org/W2144902422","https://openalex.org/W2145339207","https://openalex.org/W2145957964","https://openalex.org/W2148112459","https://openalex.org/W2160589914","https://openalex.org/W2171266831","https://openalex.org/W2173248099","https://openalex.org/W2247242831","https://openalex.org/W2342840547","https://openalex.org/W2397581010","https://openalex.org/W2751973545","https://openalex.org/W2767050701","https://openalex.org/W2770221405","https://openalex.org/W2787236409","https://openalex.org/W2788862220","https://openalex.org/W2889786920","https://openalex.org/W2898963091","https://openalex.org/W2914261249","https://openalex.org/W2949608212","https://openalex.org/W2962787969","https://openalex.org/W2962917939","https://openalex.org/W2963099939","https://openalex.org/W2963184939","https://openalex.org/W2963276097","https://openalex.org/W2963277051","https://openalex.org/W2963311874","https://openalex.org/W2963376229","https://openalex.org/W2963523627","https://openalex.org/W2963572779","https://openalex.org/W2963639957","https://openalex.org/W2963645756","https://openalex.org/W2963938771","https://openalex.org/W2964336776","https://openalex.org/W3024375163","https://openalex.org/W3037207827","https://openalex.org/W3101442004","https://openalex.org/W6605295560","https://openalex.org/W6622487243","https://openalex.org/W6628764021","https://openalex.org/W6631943919","https://openalex.org/W6638018090","https://openalex.org/W6681302627","https://openalex.org/W6681672864","https://openalex.org/W6683436435","https://openalex.org/W6684921986","https://openalex.org/W6695011786","https://openalex.org/W6704559304","https://openalex.org/W6712392314","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6718092244","https://openalex.org/W6741302124","https://openalex.org/W6756065142","https://openalex.org/W6758978475","https://openalex.org/W6760136860","https://openalex.org/W6766722902","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3205347863","https://openalex.org/W3034568050","https://openalex.org/W3212911600","https://openalex.org/W2397581010","https://openalex.org/W3015024584","https://openalex.org/W2985159211","https://openalex.org/W3132357549","https://openalex.org/W3035868808","https://openalex.org/W3130127426","https://openalex.org/W2773860117","https://openalex.org/W2954339628","https://openalex.org/W3169840145","https://openalex.org/W3172839753","https://openalex.org/W3112291329","https://openalex.org/W2950600380","https://openalex.org/W3007369745","https://openalex.org/W3029760382","https://openalex.org/W2963794592","https://openalex.org/W2947525798","https://openalex.org/W3109409708"],"abstract_inverted_index":{"State-of-the-art":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"algorithms":[4,89],"suffer":[5],"from":[6],"high":[7],"sample":[8],"complexity,":[9],"particularly":[10],"in":[11,52,143],"the":[12,134],"sparse":[13],"reward":[14],"case.":[15],"A":[16],"popular":[17],"strategy":[18],"for":[19,62,68,127],"mitigating":[20],"this":[21,56],"problem":[22,84],"is":[23,40],"to":[24,45,74,95,103],"learn":[25],"control":[26,148],"policies":[27],"by":[28,109],"imitating":[29],"a":[30,66,82,105,110,144,154],"set":[31],"of":[32,37,118,146,156],"expert":[33,43],"demonstrations.":[34],"The":[35],"drawback":[36],"such":[38,90],"approaches":[39],"that":[41],"an":[42,75],"needs":[44],"produce":[46],"demonstrations,":[47],"which":[48],"may":[49],"be":[50],"costly":[51],"practice.":[53],"To":[54],"address":[55],"shortcoming,":[57],"we":[58],"propose":[59],"Probabilistic":[60],"Planning":[61],"Demonstration":[63],"Discovery":[64],"(P2D2),":[65],"technique":[67],"automatically":[69],"discovering":[70,79],"demonstrations":[71,80,100],"without":[72],"access":[73],"expert.":[76],"We":[77,114,131],"formulate":[78],"as":[81,91,123,125],"search":[83],"and":[85,138,149,159],"leverage":[86],"widely-used":[87],"planning":[88],"Rapidly-exploring":[92],"Random":[93],"Tree":[94],"find":[96],"demonstration":[97],"trajectories.":[98],"These":[99],"are":[101],"used":[102],"initialize":[104],"policy,":[106],"then":[107],"refined":[108],"generic":[111],"RL":[112,141],"algorithm.":[113],"provide":[115],"theoretical":[116],"guarantees":[117],"P2D2":[119],"finding":[120],"successful":[121],"trajectories,":[122],"well":[124],"bounds":[126],"its":[128],"sampling":[129],"complexity.":[130],"experimentally":[132],"demonstrate":[133],"method":[135],"outperforms":[136],"classic":[137,147],"intrinsic":[139],"exploration":[140,157],"techniques":[142],"range":[145],"robotics":[150],"tasks,":[151],"requiring":[152],"only":[153],"fraction":[155],"samples":[158],"achieving":[160],"better":[161],"asymptotic":[162],"performance.":[163]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}