{"id":"https://openalex.org/W4200522801","doi":"https://doi.org/10.1109/iros51168.2021.9636167","title":"HARL-A: Hardware Agnostic Reinforcement Learning Through Adversarial Selection","display_name":"HARL-A: Hardware Agnostic Reinforcement Learning Through Adversarial Selection","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W4200522801","doi":"https://doi.org/10.1109/iros51168.2021.9636167"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636167","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5113972647","display_name":"Lucy Jackson","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lucy Jackson","raw_affiliation_strings":["University of Surrey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010795038","display_name":"Steve Eckersley","orcid":"https://orcid.org/0000-0002-9491-4385"},"institutions":[{"id":"https://openalex.org/I1283197605","display_name":"Surrey Satellite Technology (United Kingdom)","ror":"https://ror.org/01s5rx042","country_code":"GB","type":"company","lineage":["https://openalex.org/I1283197605"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Eckersley","raw_affiliation_strings":["Surrey Satellite Technology Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Surrey Satellite Technology Limited","institution_ids":["https://openalex.org/I1283197605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044201538","display_name":"Pete Senior","orcid":null},"institutions":[{"id":"https://openalex.org/I1283197605","display_name":"Surrey Satellite Technology (United Kingdom)","ror":"https://ror.org/01s5rx042","country_code":"GB","type":"company","lineage":["https://openalex.org/I1283197605"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pete Senior","raw_affiliation_strings":["Surrey Satellite Technology Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Surrey Satellite Technology Limited","institution_ids":["https://openalex.org/I1283197605"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091184063","display_name":"Simon Hadfield","orcid":"https://orcid.org/0000-0001-8637-5054"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Hadfield","raw_affiliation_strings":["University of Surrey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55888523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3499","last_page":"3505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9980999827384949,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8553026914596558},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7409422993659973},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7388231754302979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6485339403152466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5338965654373169},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5242170095443726},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4919740855693817},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4525252878665924},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4313373863697052},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4268275797367096},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4084295332431793},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09076499938964844}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8553026914596558},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409422993659973},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7388231754302979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6485339403152466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5338965654373169},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5242170095443726},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4919740855693817},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4525252878665924},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4313373863697052},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4268275797367096},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4084295332431793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09076499938964844},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros51168.2021.9636167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636167","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11151479600002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1211393779","display_name":null,"funder_award_id":"2116510","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G918011532","display_name":null,"funder_award_id":"EP/S035761/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2097381042","https://openalex.org/W2134949557","https://openalex.org/W2257979135","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2736601468","https://openalex.org/W2754517384","https://openalex.org/W2762872434","https://openalex.org/W2895958971","https://openalex.org/W2906430505","https://openalex.org/W2951762469","https://openalex.org/W2951871955","https://openalex.org/W2962974944","https://openalex.org/W2962976158","https://openalex.org/W2963280855","https://openalex.org/W2963669306","https://openalex.org/W2963864421","https://openalex.org/W2963887494","https://openalex.org/W2964262254","https://openalex.org/W2964335674","https://openalex.org/W2968116426","https://openalex.org/W3101442004","https://openalex.org/W4297810554","https://openalex.org/W4297824641","https://openalex.org/W6638018090","https://openalex.org/W6674600207","https://openalex.org/W6684921986","https://openalex.org/W6728252718","https://openalex.org/W6735677848","https://openalex.org/W6741002519","https://openalex.org/W6745190604","https://openalex.org/W6752187413","https://openalex.org/W6754782557","https://openalex.org/W6755353450","https://openalex.org/W6756463683","https://openalex.org/W6757955501","https://openalex.org/W6780559895","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,14,64,111,169,175],"reinforcement":[3],"learning":[4,84,100,143,148],"(RL)":[5],"has":[6],"led":[7],"to":[8,38,43,45,59,71,85,136,153,177],"huge":[9],"advancements":[10],"in":[11,61,73,161],"the":[12,22,81,109,166],"field":[13],"robotics.":[15],"However":[16],"data":[17],"scarcity,":[18],"brittle":[19],"convergence":[20],"and":[21,41,89,95,182],"gap":[23],"between":[24],"simulation":[25],"&":[26],"real":[27],"world":[28],"environments,":[29],"mean":[30],"that":[31,83],"most":[32],"common":[33],"RL":[34,180],"approaches":[35],"are":[36,125],"subject":[37],"over":[39],"fitting":[40],"fail":[42],"generalise":[44],"unseen":[46],"environments.":[47],"Hardware":[48,112],"agnostic":[49],"policies":[50,103],"would":[51],"mitigate":[52],"this":[53,121],"by":[54],"allowing":[55],"a":[56,62,87,128,178],"single":[57],"network":[58],"operate":[60],"variety":[63],"test":[65],"domains,":[66],"where":[67],"dynamics":[68],"vary":[69],"due":[70],"changes":[72],"robotic":[74],"morphologies":[75,139],"or":[76],"internal":[77],"parameters.":[78],"We":[79],"utilise":[80],"idea":[82,110],"adapt":[86],"known":[88],"successful":[90],"control":[91,102],"policy":[92],"is":[93,134],"easier":[94],"more":[96],"flexible":[97],"than":[98],"jointly":[99],"numerous":[101],"for":[104],"different":[105],"morphologies.This":[106],"paper":[107],"presents":[108],"Agnostic":[113],"Reinforcement":[114],"Learning":[115],"using":[116,127,165],"Adversarial":[117],"selection":[118],"(HARL-A).":[119],"In":[120],"approach":[122],"training":[123],"examples":[124],"sampled":[126],"novel":[129],"adversarial":[130],"loss":[131,151],"function.":[132],"This":[133],"designed":[135],"self":[137],"regulate":[138],"based":[140,150],"on":[141],"their":[142],"potential.":[144],"Simply":[145],"applying":[146],"our":[147],"potential":[149],"function":[152],"current":[154,186],"state-of-the-art":[155],"already":[156],"provides":[157],"~":[158],"30%":[159],"improvement":[160],"performance.":[162],"Meanwhile":[163],"experiments":[164],"full":[167],"implementation":[168],"HARL-A":[170],"report":[171],"an":[172],"average":[173],"increase":[174],"70%":[176],"standard":[179],"baseline":[181],"55%":[183],"compared":[184],"with":[185],"state-of-the-art.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}