{"id":"https://openalex.org/W4383108345","doi":"https://doi.org/10.1109/icra48891.2023.10161415","title":"Efficient Learning of High Level Plans from Play","display_name":"Efficient Learning of High Level Plans from Play","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108345","doi":"https://doi.org/10.1109/icra48891.2023.10161415"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5071357286","display_name":"N\u00faria Armengol Urp\u00ed","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"N\u00faria Armengol Urp\u00ed","raw_affiliation_strings":["ETH Zurich,Department of Computer Science,Switzerland","Department of Computer Science, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Department of Computer Science,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067784194","display_name":"Marco Bagatella","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marco Bagatella","raw_affiliation_strings":["ETH Zurich,Department of Computer Science,Switzerland","Department of Computer Science, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Department of Computer Science,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025000908","display_name":"Otmar Hilliges","orcid":"https://orcid.org/0000-0002-5068-3474"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Otmar Hilliges","raw_affiliation_strings":["ETH Zurich,Department of Computer Science,Switzerland","Department of Computer Science, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Department of Computer Science,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001474340","display_name":"Georg Martius","orcid":"https://orcid.org/0000-0002-8963-7627"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Martius","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems,Tübingen,Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems,Tübingen,Germany","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055713873","display_name":"Stelian Coros","orcid":"https://orcid.org/0000-0001-6604-4784"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Stelian Coros","raw_affiliation_strings":["ETH Zurich,Department of Computer Science,Switzerland","Department of Computer Science, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Department of Computer Science,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071357286"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06790068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10189","last_page":"10196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9986000061035156,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8610421419143677},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8247052431106567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7863648533821106},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5564155578613281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.544935941696167},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5164266228675842},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4981694221496582},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.45826393365859985},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4496496319770813},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4439725875854492},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4237244129180908},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4159667491912842},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4057149887084961},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3466249108314514}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8610421419143677},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8247052431106567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863648533821106},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5564155578613281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.544935941696167},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5164266228675842},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4981694221496582},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.45826393365859985},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4496496319770813},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4439725875854492},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4237244129180908},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4159667491912842},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4057149887084961},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3466249108314514},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321652","display_name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich","ror":"https://ror.org/05a28rw58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W107583932","https://openalex.org/W1522301498","https://openalex.org/W1529739011","https://openalex.org/W1592847719","https://openalex.org/W1595483645","https://openalex.org/W1867103660","https://openalex.org/W1941445455","https://openalex.org/W1971086298","https://openalex.org/W2000359213","https://openalex.org/W2061983716","https://openalex.org/W2070683816","https://openalex.org/W2099893201","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2128990851","https://openalex.org/W2129670787","https://openalex.org/W2142224528","https://openalex.org/W2145339207","https://openalex.org/W2160371091","https://openalex.org/W2172131460","https://openalex.org/W2256420211","https://openalex.org/W2560674852","https://openalex.org/W2601322194","https://openalex.org/W2739341730","https://openalex.org/W2788030459","https://openalex.org/W2788862220","https://openalex.org/W2810228177","https://openalex.org/W2810785043","https://openalex.org/W2891217993","https://openalex.org/W2912185451","https://openalex.org/W2950614095","https://openalex.org/W2963696152","https://openalex.org/W2981030070","https://openalex.org/W2990747716","https://openalex.org/W2996037775","https://openalex.org/W2996896271","https://openalex.org/W3006033038","https://openalex.org/W3034563340","https://openalex.org/W3034808834","https://openalex.org/W3092663687","https://openalex.org/W3093784640","https://openalex.org/W3128894241","https://openalex.org/W3132442447","https://openalex.org/W3154938165","https://openalex.org/W3202678378","https://openalex.org/W3204657926","https://openalex.org/W3206530605","https://openalex.org/W3206771627","https://openalex.org/W4213251304","https://openalex.org/W4225873172","https://openalex.org/W4286891527","https://openalex.org/W4287209565","https://openalex.org/W4287630848","https://openalex.org/W4288331462","https://openalex.org/W4293160779","https://openalex.org/W4295352814","https://openalex.org/W4300799055","https://openalex.org/W4312253354","https://openalex.org/W6616173779","https://openalex.org/W6631190155","https://openalex.org/W6635701881","https://openalex.org/W6679046149","https://openalex.org/W6683821272","https://openalex.org/W6684863604","https://openalex.org/W6691861496","https://openalex.org/W6713184877","https://openalex.org/W6735944222","https://openalex.org/W6740801417","https://openalex.org/W6748839928","https://openalex.org/W6751720535","https://openalex.org/W6752089545","https://openalex.org/W6753243525","https://openalex.org/W6755612348","https://openalex.org/W6760439459","https://openalex.org/W6764173040","https://openalex.org/W6769035977","https://openalex.org/W6772005887","https://openalex.org/W6779526804","https://openalex.org/W6784521679","https://openalex.org/W6784712800","https://openalex.org/W6784881954","https://openalex.org/W6785876034","https://openalex.org/W6798895900","https://openalex.org/W6802864926","https://openalex.org/W6810063815"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2768698792","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W4310614650","https://openalex.org/W4386738330"],"abstract_inverted_index":{"Real-world":[0],"robotic":[1,79],"manipulation":[2,92,158],"tasks":[3,133,159],"remain":[4,42],"an":[5],"elusive":[6],"challenge,":[7],"since":[8],"they":[9,41],"involve":[10],"both":[11],"fine-grained":[12],"environment":[13],"interaction,":[14],"as":[15,17,126],"well":[16],"the":[18,55,112,137],"ability":[19],"to":[20,50,88,99,129,140,168],"plan":[21],"for":[22,78],"long-horizon":[23,90,132],"goals.":[24],"Although":[25],"deep":[26,86],"reinforcement":[27],"learning":[28,80],"(RL)":[29],"methods":[30],"have":[31],"shown":[32],"encouraging":[33],"results":[34],"when":[35],"planning":[36,84],"end-to-end":[37],"in":[38],"high-dimensional":[39],"environments,":[40],"fundamentally":[43],"limited":[44],"by":[45,54],"poor":[46],"sample":[47,150],"efficiency":[48,151],"due":[49],"inefficient":[51],"exploration,":[52],"and":[53,85,134,160],"complexity":[56],"of":[57,70],"credit":[58],"assignment":[59],"over":[60,105,155],"long":[61],"horizons.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"present":[67],"Efficient":[68],"Learning":[69],"High-Level":[71],"Plans":[72],"from":[73],"Play":[74],"(ELF-P),":[75],"a":[76,101,118],"framework":[77],"that":[81,145,163],"bridges":[82],"motion":[83],"RL":[87],"achieve":[89],"complex":[91,131],"tasks.":[93],"We":[94,115,143],"leverage":[95],"task-agnostic":[96],"play":[97],"data":[98],"learn":[100],"discrete":[102],"behavioral":[103,138],"prior":[104,139],"object-centric":[106],"primitives,":[107],"modeling":[108],"their":[109],"feasibility":[110],"given":[111],"current":[113],"context.":[114],"then":[116],"design":[117],"high-level":[119],"goal-conditioned":[120],"policy":[121],"which":[122],"(1)":[123],"uses":[124],"primitives":[125],"building":[127],"blocks":[128],"scaffold":[130],"(2)":[135],"leverages":[136],"accelerate":[141],"learning.":[142],"demonstrate":[144],"ELF-P":[146],"has":[147],"significantly":[148],"better":[149],"than":[152],"relevant":[153],"baselines":[154],"multiple":[156],"realistic":[157],"learns":[161],"policies":[162],"can":[164],"be":[165],"easily":[166],"transferred":[167],"physical":[169],"hardware.":[170]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}