{"id":"https://openalex.org/W4383097626","doi":"https://doi.org/10.1109/icra48891.2023.10160791","title":"Efficiently Learning Small Policies for Locomotion and Manipulation","display_name":"Efficiently Learning Small Policies for Locomotion and Manipulation","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383097626","doi":"https://doi.org/10.1109/icra48891.2023.10160791"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160791","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10160791","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":"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/A5076797247","display_name":"Shashank Hegde","orcid":"https://orcid.org/0000-0003-1700-5425"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shashank Hegde","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077367921","display_name":"Gaurav S. Sukhatme","orcid":"https://orcid.org/0000-0003-2408-474X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav S. Sukhatme","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41123069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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":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/T10653","display_name":"Robot Manipulation and Learning","score":0.9563000202178955,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9215999841690063,"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/computer-science","display_name":"Computer science","score":0.8085163235664368},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8052193522453308},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7495409846305847},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6281251907348633},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5957966446876526},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5380973219871521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5349105000495911},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.482643187046051},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4812721610069275},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4610774517059326},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4433441162109375},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.43883687257766724},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34512728452682495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085163235664368},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8052193522453308},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7495409846305847},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6281251907348633},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5957966446876526},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5380973219871521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5349105000495911},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.482643187046051},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4812721610069275},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4610774517059326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4433441162109375},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.43883687257766724},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34512728452682495},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160791","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10160791","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2119814172","https://openalex.org/W2158782408","https://openalex.org/W2575705757","https://openalex.org/W2739330054","https://openalex.org/W2748216408","https://openalex.org/W2781726626","https://openalex.org/W2885311373","https://openalex.org/W2897818259","https://openalex.org/W2907537824","https://openalex.org/W2963864421","https://openalex.org/W3029541954","https://openalex.org/W3126321819","https://openalex.org/W3199349421","https://openalex.org/W4206742276","https://openalex.org/W4214717370","https://openalex.org/W4286895466","https://openalex.org/W4293872189","https://openalex.org/W4300799055","https://openalex.org/W6684921986","https://openalex.org/W6740801417","https://openalex.org/W6743285051","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6753278433","https://openalex.org/W6755501315","https://openalex.org/W6763328670","https://openalex.org/W6780559895","https://openalex.org/W6801377368","https://openalex.org/W6802998458","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W2468279273","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W4318559728","https://openalex.org/W3183136280","https://openalex.org/W4281847915","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Neural":[0],"control":[1],"of":[2,34,89,95,108,142],"memory-constrained,":[3],"agile":[4],"robots":[5],"requires":[6],"small,":[7],"yet":[8,41],"highly":[9],"performant":[10],"models.":[11],"We":[12,57],"leverage":[13],"graph":[14,19],"hyper":[15,20],"networks":[16,29,40,51],"to":[17,45,65,99,131],"learn":[18],"policies":[21,43,113],"trained":[22,52],"with":[23,92,114],"off-policy":[24,67],"reinforcement":[25,68],"learning":[26,69],"resulting":[27],"in":[28,74],"that":[30,59],"are":[31],"two":[32],"orders":[33],"magnitude":[35],"smaller":[36],"than":[37],"commonly":[38],"used":[39],"encode":[42],"comparable":[44],"those":[46],"encoded":[47],"by":[48,76],"much":[49],"larger":[50],"on":[53,139],"the":[54,105,133,140],"same":[55],"task.":[56],"show":[58],"our":[60,115],"method":[61,116,130],"can":[62],"be":[63],"appended":[64],"any":[66,72],"algorithm,":[70],"without":[71],"change":[73],"hyperparameters,":[75],"showing":[77],"results":[78],"across":[79],"locomotion":[80],"and":[81],"manipulation":[82],"tasks.":[83],"Further,":[84],"we":[85,127],"obtain":[86],"an":[87,101],"array":[88],"working":[90],"policies,":[91],"differing":[93],"numbers":[94],"parameters,":[96],"allowing":[97],"us":[98],"pick":[100],"optimal":[102],"network":[103],"for":[104],"memory":[106],"constraints":[107],"a":[109,123,129,137],"system.":[110],"Training":[111],"multiple":[112],"is":[117],"as":[118,121],"sample":[119],"efficient":[120],"training":[122],"single":[124],"policy.":[125],"Finally,":[126],"provide":[128],"select":[132],"best":[134],"architecture,":[135],"given":[136],"constraint":[138],"number":[141],"parameters.":[143],"Project":[144],"website:":[145],"https://sites.google.com/usc.edu/graphhyperpolicy":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}