{"id":"https://openalex.org/W3028313495","doi":null,"title":"Dynamics-Aware Latent Space Reachability for Exploration in Temporally-Extended Tasks.","display_name":"Dynamics-Aware Latent Space Reachability for Exploration in Temporally-Extended Tasks.","publication_year":2020,"publication_date":"2020-05-21","ids":{"openalex":"https://openalex.org/W3028313495","mag":"3028313495"},"language":"en","primary_location":{"id":"mag:3028313495","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.10934","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.10934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064794691","display_name":"Homanga Bharadhwaj","orcid":"https://orcid.org/0000-0001-5056-8516","observed_orcids":["https://orcid.org/0000-0001-5056-8516"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Homanga Bharadhwaj","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5056-8516","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296","observed_orcids":["https://orcid.org/0000-0003-0482-4296"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Animesh Garg","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0482-4296","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010648258","display_name":"Florian Shkurti","orcid":"https://orcid.org/0000-0002-5672-5831","observed_orcids":["https://orcid.org/0000-0002-5672-5831"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Shkurti","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5672-5831","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10653","display_name":"Robot Manipulation and Learning","score":9.999999747378752e-05,"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/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/policy-learning","display_name":"policy learning","score":0.38199999928474426},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.6859999895095825},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.7120000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7167658805847168},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.7009977102279663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5548405647277832},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5429719090461731},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5284625887870789},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5230960845947266},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.505441427230835},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46977704763412476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4448294937610626},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4277935326099396},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4231388568878174},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.416472852230072},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24398568272590637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1902729570865631},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11232736706733704},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3028313495","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.10934","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3028313495","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.10934","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1522301498","https://openalex.org/W1594201624","https://openalex.org/W1966213627","https://openalex.org/W1968962398","https://openalex.org/W2107667896","https://openalex.org/W2151834591","https://openalex.org/W2201912979","https://openalex.org/W2210483910","https://openalex.org/W2296073425","https://openalex.org/W2514775068","https://openalex.org/W2528489519","https://openalex.org/W2614839826","https://openalex.org/W2616430965","https://openalex.org/W2733961795","https://openalex.org/W2736601468","https://openalex.org/W2753738274","https://openalex.org/W2760003929","https://openalex.org/W2766614170","https://openalex.org/W2781726626","https://openalex.org/W2786487443","https://openalex.org/W2787938642","https://openalex.org/W2804010078","https://openalex.org/W2823112946","https://openalex.org/W2886380293","https://openalex.org/W2899771611","https://openalex.org/W2900928600","https://openalex.org/W2914261249","https://openalex.org/W2922007426","https://openalex.org/W2923252998","https://openalex.org/W2938421504","https://openalex.org/W2947638559","https://openalex.org/W2949608212","https://openalex.org/W2950004691","https://openalex.org/W2963276097","https://openalex.org/W2963430173","https://openalex.org/W2964112890","https://openalex.org/W2970534317","https://openalex.org/W2970971581","https://openalex.org/W2975141838","https://openalex.org/W2980555752","https://openalex.org/W2981030070","https://openalex.org/W2992977009","https://openalex.org/W3010884024","https://openalex.org/W3015437096","https://openalex.org/W3023640063","https://openalex.org/W3025660841","https://openalex.org/W3090834423","https://openalex.org/W3091905774","https://openalex.org/W3098053103"],"related_works":["https://openalex.org/W3035992805","https://openalex.org/W2786917922","https://openalex.org/W4388514351","https://openalex.org/W2948199691","https://openalex.org/W4416222983","https://openalex.org/W4287215707","https://openalex.org/W3128801224","https://openalex.org/W4403586101","https://openalex.org/W4415797440","https://openalex.org/W33445057"],"abstract_inverted_index":{"Self-supervised":[0],"goal":[1,23,80,108],"proposal":[2],"and":[3,29,74,107,113,127],"reaching":[4],"is":[5,145,152],"a":[6,15,50,57,64,139,169,179,214,222],"key":[7],"component":[8],"of":[9,53,70,89,94,102,124,133,171,216],"efficient":[10],"policy":[11,103],"learning":[12,104],"algorithms.":[13],"Such":[14],"self-supervised":[16,199],"approach":[17],"without":[18],"access":[19,118],"to":[20,77,119,147,186,210],"any":[21,117],"oracle":[22],"sampling":[24,182],"distribution":[25],"requires":[26],"deep":[27],"exploration":[28,46,84,200],"commitment":[30],"so":[31],"that":[32,144,175,196],"long":[33],"horizon":[34],"plans":[35],"can":[36,202],"be":[37],"efficiently":[38],"discovered.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,137,167,194],"propose":[44,138],"an":[45,164],"framework,":[47],"which":[48],"learns":[49],"dynamics-aware":[51],"manifold":[52],"reachable":[54,71,91,134,153,172],"states.":[55],"Given":[56],"new":[58],"goal,":[59],"our":[60],"proposed":[61,198],"method":[62],"visits":[63],"state":[65,151],"at":[66],"the":[67,79,87,90,99,120,125,128,157,187,197],"current":[68],"frontier":[69,88,170],"states":[72,109,123,173],"(commitment/reaching)":[73],"then":[75],"explores":[76],"reach":[78],"(exploration).":[81],"This":[82],"allocates":[83],"budget":[85],"near":[86],"region":[92],"instead":[93],"its":[95],"interior.":[96],"We":[97],"target":[98],"challenging":[100,217],"problem":[101],"from":[105,154,174],"initial":[106,165],"specified":[110,158],"as":[111],"images,":[112],"do":[114],"not":[115],"assume":[116],"underlying":[121],"ground-truth":[122],"robot":[126,224],"environment.":[129],"To":[130],"keep":[131],"track":[132],"latent":[135,159],"states,":[136],"distance":[140],"conditioned":[141],"reachability":[142],"network":[143],"trained":[146],"infer":[148],"whether":[149],"one":[150],"another":[155],"within":[156],"space":[160],"distance.":[161],"So,":[162],"given":[163],"state,":[166],"obtain":[168],"state.":[176],"By":[177],"incorporating":[178],"curriculum":[180],"for":[181],"easier":[183],"goals":[184],"(closer":[185],"start":[188],"state)":[189],"before":[190],"more":[191],"difficult":[192],"goals,":[193],"demonstrate":[195],"algorithm,":[201],"achieve":[203],"20%":[204],"superior":[205],"performance":[206],"on":[207,213,221],"average":[208],"compared":[209],"existing":[211],"baselines":[212],"set":[215],"robotic":[218],"environments,":[219],"including":[220],"real":[223],"manipulation":[225],"task.":[226]},"counts_by_year":[{"year":2020,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-05-29T00:00:00"}