{"id":"https://openalex.org/W4401417407","doi":"https://doi.org/10.1109/icra57147.2024.10610861","title":"HyperPPO: A scalable method for finding small policies for robotic control","display_name":"HyperPPO: A scalable method for finding small policies for robotic control","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401417407","doi":"https://doi.org/10.1109/icra57147.2024.10610861"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610861","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610861","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/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":"middle","author":{"id":"https://openalex.org/A5011327397","display_name":"Zhehui Huang","orcid":null},"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":"Zhehui Huang","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":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52702607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"164","issue":null,"first_page":"10821","last_page":"10828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9977999925613403,"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":0.9973000288009644,"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":0.712101936340332},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6891143918037415},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5580393671989441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25304466485977173},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12536996603012085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.712101936340332},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6891143918037415},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5580393671989441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25304466485977173},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12536996603012085}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610861","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610861","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":[{"display_name":"Decent work and economic growth","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2758653969","https://openalex.org/W2907537824","https://openalex.org/W2963796870","https://openalex.org/W2963864421","https://openalex.org/W3003669699","https://openalex.org/W3009352231","https://openalex.org/W3108223837","https://openalex.org/W3202883604","https://openalex.org/W3205509561","https://openalex.org/W4206742276","https://openalex.org/W4283311772","https://openalex.org/W4286895466","https://openalex.org/W4300799055","https://openalex.org/W4317838087","https://openalex.org/W4366330381","https://openalex.org/W4378506727","https://openalex.org/W4378942764","https://openalex.org/W4381245790","https://openalex.org/W4383097626","https://openalex.org/W4401416687","https://openalex.org/W6684921986","https://openalex.org/W6729956949","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6743495212","https://openalex.org/W6747473740","https://openalex.org/W6752515464","https://openalex.org/W6755501315","https://openalex.org/W6757380569","https://openalex.org/W6774176488","https://openalex.org/W6779282036","https://openalex.org/W6780153092","https://openalex.org/W6780559895","https://openalex.org/W6792048375","https://openalex.org/W6797154179","https://openalex.org/W6800004206","https://openalex.org/W6801377368","https://openalex.org/W6801964084","https://openalex.org/W6802998458","https://openalex.org/W6839361920","https://openalex.org/W6840541611","https://openalex.org/W6849292070","https://openalex.org/W6852609763","https://openalex.org/W6852852076","https://openalex.org/W6853193030","https://openalex.org/W6854162696","https://openalex.org/W6864424756","https://openalex.org/W7048047797"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2389214306","https://openalex.org/W4396696052","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Models":[0],"with":[1],"fewer":[2],"parameters":[3],"are":[4,51,119],"necessary":[5],"for":[6,48],"the":[7,37,70,79,81,113],"neural":[8,17,41,114],"control":[9,123],"of":[10,39,83,121,124],"memory-limited,":[11],"performant":[12,62],"robots.":[13],"Finding":[14],"these":[15],"smaller":[16,53],"network":[18,86],"architectures":[19,42],"can":[20],"be":[21],"time-consuming.":[22],"We":[23,64,93,110],"propose":[24],"HyperPPO,":[25],"an":[26],"on-policy":[27],"reinforcement":[28],"learning":[29],"algorithm":[30],"that":[31,50,88,95,112],"utilizes":[32],"graph":[33],"hypernetworks":[34],"to":[35,107],"estimate":[36],"weights":[38,47],"multiple":[40,66],"simultaneously.":[43],"Our":[44],"method":[45,97],"estimates":[46],"networks":[49,58],"much":[52],"than":[54],"those":[55],"in":[56],"common-use":[57],"yet":[59],"encode":[60],"highly":[61],"policies.":[63],"obtain":[65],"trained":[67],"policies":[68,115],"at":[69],"same":[71],"time":[72],"while":[73],"maintaining":[74],"sample":[75],"efficiency":[76],"and":[77],"provide":[78],"user":[80],"choice":[82],"picking":[84],"a":[85,125],"architecture":[87],"satisfies":[89],"their":[90],"computational":[91],"constraints.":[92],"show":[94],"our":[96],"scales":[98],"well":[99],"-":[100],"more":[101],"training":[102],"resources":[103],"produce":[104],"faster":[105],"convergence":[106],"higher-performing":[108],"architectures.":[109],"demonstrate":[111],"estimated":[116],"by":[117],"HyperPPO":[118],"capable":[120],"decentralized":[122],"Crazyflie2.1":[126],"quadrotor.":[127],"Website:":[128],"https://sites.google.com/usc.edu/hyperppo":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}