{"id":"https://openalex.org/W3030163244","doi":"https://doi.org/10.48550/arxiv.1908.05224","title":"Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real","display_name":"Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real","publication_year":2019,"publication_date":"2019-08-13","ids":{"openalex":"https://openalex.org/W3030163244","doi":"https://doi.org/10.48550/arxiv.1908.05224","mag":"3030163244"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1908.05224","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.05224","pdf_url":"https://arxiv.org/pdf/1908.05224","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/1908.05224","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057773393","display_name":"Ofir Nachum","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nachum, Ofir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ahn, Michael","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahn, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003357030","display_name":"Hugo Ponte","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ponte, Hugo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061613634","display_name":"Shixiang Gu","orcid":"https://orcid.org/0000-0001-9246-0896","observed_orcids":["https://orcid.org/0000-0001-9246-0896"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Shixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101582321","display_name":"Vikash Kumar","orcid":"https://orcid.org/0000-0003-0284-0823","observed_orcids":["https://orcid.org/0000-0003-0284-0823"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Vikash","raw_affiliation_strings":[],"raw_orcid":null,"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":true,"cited_by_count":73,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"110","last_page":"121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0027000000700354576,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/locomotion","display_name":"locomotion","score":0.7110000252723694},{"id":"https://openalex.org/keywords/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.8870000243186951},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.8050000071525574},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.7670000195503235},{"id":"https://openalex.org/keywords/domain-randomization","display_name":"domain randomization","score":0.9779999852180481},{"id":"https://openalex.org/keywords/mobile-robots","display_name":"mobile robots","score":0.6039999723434448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.731288731098175},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.718883752822876},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6177160143852234},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5837554335594177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.556975245475769},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5019176006317139},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4989464282989502},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.4438612461090088},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.44162362813949585},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44078564643859863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43121224641799927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3259155750274658},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07751643657684326},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1908.05224","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.05224","pdf_url":"https://arxiv.org/pdf/1908.05224","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.1908.05224","doi":"https://doi.org/10.48550/arxiv.1908.05224","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.05224","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:3030163244","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/journals/corr/corr1908.html#abs-1908-05224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.05224","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.05224","pdf_url":"https://arxiv.org/pdf/1908.05224","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/W3030163244.pdf","grobid_xml":"https://content.openalex.org/works/W3030163244.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1499277207","https://openalex.org/W1503892960","https://openalex.org/W1549323854","https://openalex.org/W1771410628","https://openalex.org/W1969366849","https://openalex.org/W1987864653","https://openalex.org/W2054577881","https://openalex.org/W2065238107","https://openalex.org/W2077673559","https://openalex.org/W2110612452","https://openalex.org/W2119567691","https://openalex.org/W2139053308","https://openalex.org/W2157411165","https://openalex.org/W2158782408","https://openalex.org/W2161697934","https://openalex.org/W2169222380","https://openalex.org/W2416477367","https://openalex.org/W2565902248","https://openalex.org/W2605102758","https://openalex.org/W2738249180","https://openalex.org/W2757631751","https://openalex.org/W2781726626","https://openalex.org/W2803281228","https://openalex.org/W2805031923","https://openalex.org/W2808844346","https://openalex.org/W2905464683","https://openalex.org/W2938421504","https://openalex.org/W2938834661","https://openalex.org/W2948443723","https://openalex.org/W2949608212","https://openalex.org/W2962749646","https://openalex.org/W2962823158","https://openalex.org/W2963184939","https://openalex.org/W2963339188","https://openalex.org/W2966564143","https://openalex.org/W2990747716","https://openalex.org/W3003817470","https://openalex.org/W6922311491"],"related_works":["https://openalex.org/W4406603882","https://openalex.org/W4415251366","https://openalex.org/W4315640913","https://openalex.org/W7168536858","https://openalex.org/W4397028883","https://openalex.org/W4383109464","https://openalex.org/W4405927045","https://openalex.org/W7160625947","https://openalex.org/W7084143275","https://openalex.org/W2941355767"],"abstract_inverted_index":{"Manipulation":[0],"and":[1,114],"locomotion":[2],"are":[3,8,56],"closely":[4],"related":[5],"problems":[6],"that":[7],"often":[9],"studied":[10],"in":[11,70,83,133],"isolation.":[12],"In":[13],"this":[14],"work,":[15],"we":[16],"study":[17],"the":[18,39,60,80,95,104],"problem":[19],"of":[20,41,89,106,126],"coordinating":[21],"multiple":[22],"mobile":[23],"agents":[24],"to":[25,50,79,98,100],"exhibit":[26],"manipulation":[27,132],"behaviors":[28,97],"using":[29],"a":[30,45,64,84,109,124,134],"reinforcement":[31],"learning":[32,113],"(RL)":[33],"approach.":[34],"Our":[35],"method":[36,122],"hinges":[37],"on":[38,123],"use":[40,105],"hierarchical":[42,74],"sim2real":[43],"--":[44],"simulated":[46],"environment":[47],"is":[48,76],"used":[49,58],"learn":[51],"low-level":[52],"goal-reaching":[53],"skills,":[54],"which":[55],"then":[57,77],"as":[59],"action":[61],"space":[62],"for":[63,112],"high-level":[65],"RL":[66],"controller,":[67],"also":[68],"trained":[69],"simulation.":[71],"The":[72,87],"full":[73],"policy":[75],"transferred":[78],"real":[81],"world":[82],"zero-shot":[85],"fashion.":[86],"application":[88],"domain":[90],"randomization":[91],"during":[92],"training":[93],"enables":[94],"learned":[96],"generalize":[99],"real-world":[101,127],"settings,":[102],"while":[103],"hierarchy":[107],"provides":[108],"modular":[110],"paradigm":[111],"transferring":[115],"increasingly":[116],"complex":[117],"behaviors.":[118],"We":[119],"evaluate":[120],"our":[121],"number":[125],"tasks,":[128],"including":[129],"coordinated":[130],"object":[131],"multi-agent":[135],"setting.":[136],"See":[137],"videos":[138],"at":[139],"https://sites.google.com/view/manipulation-via-locomotion":[140]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2020-06-05T00:00:00"}