{"id":"https://openalex.org/W3171575163","doi":"https://doi.org/10.1109/icra48506.2021.9561607","title":"Shaped Policy Search for Evolutionary Strategies using Waypoints","display_name":"Shaped Policy Search for Evolutionary Strategies using Waypoints","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3171575163","doi":"https://doi.org/10.1109/icra48506.2021.9561607","mag":"3171575163"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.14639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024597534","display_name":"Kiran Lekkala","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiran Lekkala","raw_affiliation_strings":["University of Southern California,ILab,Department of Computer Science,USA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,ILab,Department of Computer Science,USA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054494771","display_name":"Laurent Itti","orcid":"https://orcid.org/0000-0002-0168-2977"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laurent Itti","raw_affiliation_strings":["University of Southern California,ILab,Department of Computer Science, Psychology and NGP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,ILab,Department of Computer Science, Psychology and NGP","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9093","last_page":"9100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/parallelizable-manifold","display_name":"Parallelizable manifold","score":0.9077516794204712},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8378174304962158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7215539216995239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5343937277793884},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5222072005271912},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.484110951423645},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4545319676399231},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4382185935974121},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.4129774570465088},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37446293234825134},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.141160786151886},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13841435313224792},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07104381918907166}],"concepts":[{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.9077516794204712},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8378174304962158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215539216995239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343937277793884},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5222072005271912},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.484110951423645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4545319676399231},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4382185935974121},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.4129774570465088},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37446293234825134},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.141160786151886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13841435313224792},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07104381918907166},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.14639","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.14639","pdf_url":"https://arxiv.org/pdf/2105.14639","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3171575163","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.14639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"doi:10.48550/arxiv.2105.14639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.14639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.14639","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.14639","pdf_url":"https://arxiv.org/pdf/2105.14639","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3171575163.pdf","grobid_xml":"https://content.openalex.org/works/W3171575163.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W155952036","https://openalex.org/W2137104525","https://openalex.org/W2151965738","https://openalex.org/W2158782408","https://openalex.org/W2596367596","https://openalex.org/W2767621168","https://openalex.org/W2946426880","https://openalex.org/W2950226226","https://openalex.org/W2951226532","https://openalex.org/W2962957031","https://openalex.org/W2963411833","https://openalex.org/W2964001908","https://openalex.org/W3001975179","https://openalex.org/W3042058594","https://openalex.org/W3044004758","https://openalex.org/W3131031071","https://openalex.org/W6637567504","https://openalex.org/W6640174482","https://openalex.org/W6682262322","https://openalex.org/W6702989015","https://openalex.org/W6735641298","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6745935785","https://openalex.org/W6762760680","https://openalex.org/W6762880109","https://openalex.org/W6763009506","https://openalex.org/W6773029903","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3205998058","https://openalex.org/W3159504712","https://openalex.org/W3210048194","https://openalex.org/W2970479807","https://openalex.org/W2947525798","https://openalex.org/W2124674171","https://openalex.org/W3028695364","https://openalex.org/W2147032798","https://openalex.org/W2997896361","https://openalex.org/W2107992190","https://openalex.org/W3174253219","https://openalex.org/W2579277897","https://openalex.org/W3009357917","https://openalex.org/W76312321","https://openalex.org/W3194008324","https://openalex.org/W3045714531","https://openalex.org/W3113148284","https://openalex.org/W3034974382","https://openalex.org/W2900238406","https://openalex.org/W2963245685"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,41,73],"try":[4],"to":[5,17,52,69],"improve":[6],"exploration":[7],"in":[8,65],"Blackbox":[9],"methods,":[10],"particularly":[11],"Evolution":[12],"strategies":[13,29],"(ES),":[14],"when":[15],"applied":[16],"Reinforcement":[18],"Learning":[19],"(RL)":[20],"problems":[21],"where":[22],"intermediate":[23],"waypoints/subgoals":[24],"are":[25,30,62],"available.":[26],"Since":[27],"Evolutionary":[28],"highly":[31],"parallelizable,":[32],"instead":[33],"of":[34,56],"extracting":[35],"just":[36],"a":[37],"scalar":[38],"cumulative":[39],"reward,":[40],"use":[42],"the":[43,47,54,57,66],"state-action":[44],"pairs":[45],"from":[46,85],"trajectories":[48],"obtained":[49],"during":[50],"rollouts/evaluations,":[51],"learn":[53],"dynamics":[55,61],"agent.":[58],"The":[59],"learnt":[60],"then":[63],"used":[64],"optimization":[67],"procedure":[68],"speed-up":[70],"training.":[71],"Lastly,":[72],"show":[74],"how":[75],"our":[76],"proposed":[77],"approach":[78],"is":[79],"universally":[80],"applicable":[81],"by":[82],"presenting":[83],"results":[84],"experiments":[86],"conducted":[87],"on":[88],"Carla":[89],"driving":[90],"and":[91],"UR5":[92],"robotic":[93],"arm":[94],"simulators.":[95]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}