{"id":"https://openalex.org/W4401414678","doi":"https://doi.org/10.1109/icra57147.2024.10610297","title":"Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots","display_name":"Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414678","doi":"https://doi.org/10.1109/icra57147.2024.10610297"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610297","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5054636066","display_name":"Thomas Lampe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Lampe","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007133617","display_name":"Abbas Abdolmaleki","orcid":"https://orcid.org/0000-0001-6692-5856"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Abbas Abdolmaleki","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090921029","display_name":"Sarah Bechtle","orcid":"https://orcid.org/0000-0002-1705-3147"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sarah Bechtle","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082738872","display_name":"Sandy H. Huang","orcid":"https://orcid.org/0000-0001-8920-2247"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sandy H. Huang","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017985443","display_name":"Jost Tobias Springenberg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jost Tobias Springenberg","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004482443","display_name":"Michael Bloesch","orcid":"https://orcid.org/0000-0002-2171-696X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Bloesch","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056401069","display_name":"Oliver Groth","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Groth","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018196238","display_name":"Roland Hafner","orcid":"https://orcid.org/0000-0001-8061-8828"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roland Hafner","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026388725","display_name":"Tim Hertweck","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Hertweck","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053312475","display_name":"Michael Neunert","orcid":"https://orcid.org/0000-0003-2080-8376"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Neunert","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002747297","display_name":"Markus Wulfmeier","orcid":"https://orcid.org/0000-0003-1802-4492"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Markus Wulfmeier","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434263","display_name":"Jingwei Zhang","orcid":"https://orcid.org/0000-0002-1681-6608"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jingwei Zhang","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063532849","display_name":"Francesco Nori","orcid":"https://orcid.org/0000-0003-3763-6873"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francesco Nori","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062951341","display_name":"Nicolas Heess","orcid":"https://orcid.org/0000-0001-7876-9256"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicolas Heess","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin Riedmiller","raw_affiliation_strings":["Google DeepMind,London,N1C4AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,N1C4AG","institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"7772","last_page":"7779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9925000071525574,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7777203917503357},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.7124224901199341},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.70272296667099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6499364972114563},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5944698452949524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5347126722335815},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32131484150886536},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08733108639717102},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05147102475166321},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.04690897464752197}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7777203917503357},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.7124224901199341},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.70272296667099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499364972114563},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5944698452949524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5347126722335815},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32131484150886536},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08733108639717102},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05147102475166321},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.04690897464752197},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610297","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1969074599","https://openalex.org/W2047191624","https://openalex.org/W2133853511","https://openalex.org/W2155007355","https://openalex.org/W2194775991","https://openalex.org/W2735995851","https://openalex.org/W2810785043","https://openalex.org/W2963133245","https://openalex.org/W2963713397","https://openalex.org/W2964006217","https://openalex.org/W3006904299","https://openalex.org/W3033324992","https://openalex.org/W3037440645","https://openalex.org/W3040490156","https://openalex.org/W3040518754","https://openalex.org/W3091471537","https://openalex.org/W3171176697","https://openalex.org/W4221164312","https://openalex.org/W4225918202","https://openalex.org/W4298174377","https://openalex.org/W4312326293","https://openalex.org/W4313598235","https://openalex.org/W4323066621","https://openalex.org/W4385430486","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W4394674699","https://openalex.org/W6639949747","https://openalex.org/W6640174482","https://openalex.org/W6682849425","https://openalex.org/W6683300800","https://openalex.org/W6685726866","https://openalex.org/W6732837357","https://openalex.org/W6740879895","https://openalex.org/W6745983339","https://openalex.org/W6747473740","https://openalex.org/W6747924173","https://openalex.org/W6748523217","https://openalex.org/W6753243525","https://openalex.org/W6757469721","https://openalex.org/W6773027235","https://openalex.org/W6773930613","https://openalex.org/W6777357929","https://openalex.org/W6779265984","https://openalex.org/W6780159193","https://openalex.org/W6793841834","https://openalex.org/W6802395018","https://openalex.org/W6803699115","https://openalex.org/W6810285496","https://openalex.org/W6810816574","https://openalex.org/W6848774067","https://openalex.org/W6850300045","https://openalex.org/W6854738657"],"related_works":["https://openalex.org/W2035329725","https://openalex.org/W4376641153","https://openalex.org/W2070875936","https://openalex.org/W4250391473","https://openalex.org/W3045075405","https://openalex.org/W4302292679","https://openalex.org/W4241625287","https://openalex.org/W2050788868","https://openalex.org/W4295885776","https://openalex.org/W2027634686"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,15,31,56,81],"solely":[2],"from":[3,32,82,112],"an":[4,62],"agent\u2019s":[5],"self-generated":[6],"data":[7,24,34],"is":[8],"often":[9],"believed":[10],"to":[11,20],"be":[12,36],"infeasible":[13],"for":[14],"on":[16,99,118],"real":[17,33,83,103],"robots,":[18],"due":[19],"the":[21,51,76,88,94,97],"amount":[22],"of":[23,54,96],"needed.":[25],"However,":[26],"if":[27],"done":[28],"right,":[29],"agents":[30],"can":[35,69],"surprisingly":[37],"efficient":[38],"through":[39],"re-using":[40],"previously":[41],"collected":[42,77],"sub-optimal":[43],"data.":[44],"In":[45],"this":[46],"paper":[47],"we":[48],"demonstrate":[49],"how":[50],"increased":[52],"understanding":[53],"off-policy":[55],"methods":[57],"and":[58,67,114],"their":[59],"embedding":[60],"in":[61],"iterative":[63],"online/offline":[64],"scheme":[65],"(\"collect":[66],"infer\")":[68],"drastically":[70],"improve":[71],"data-efficiency":[72],"by":[73],"using":[74],"all":[75],"experience,":[78],"which":[79],"empowers":[80],"robot":[84,104],"experience":[85],"only.":[86],"Moreover,":[87],"resulting":[89],"policy":[90],"improves":[91],"significantly":[92],"over":[93],"state":[95],"art":[98],"a":[100,125],"recently":[101],"proposed":[102],"manipulation":[105],"benchmark.":[106],"Our":[107],"approach":[108],"learns":[109],"end-to-end,":[110],"directly":[111],"pixels,":[113],"does":[115],"not":[116],"rely":[117],"additional":[119],"human":[120],"domain":[121],"knowledge":[122],"such":[123],"as":[124],"simulator":[126],"or":[127],"demonstrations.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}