{"id":"https://openalex.org/W7163517727","doi":"https://doi.org/10.1109/lra.2026.3700381","title":"MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics","display_name":"MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163517727","doi":"https://doi.org/10.1109/lra.2026.3700381"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3700381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3700381","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","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/A5137852789","display_name":"Neil Janwani","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Janwani","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0009-0000-7661-4736","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137837093","display_name":"Ellen Novoseller","orcid":null},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ellen Novoseller","raw_affiliation_strings":["DEVCOM Army Research Laboratory, Adelphi, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-5263-0598","affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051690828","display_name":"Vernon J. Lawhern","orcid":"https://orcid.org/0000-0002-3921-8723"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vernon J. Lawhern","raw_affiliation_strings":["DEVCOM Army Research Laboratory, Adelphi, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-3921-8723","affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054944952","display_name":"Maegan Tucker","orcid":"https://orcid.org/0000-0001-7363-6809"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maegan Tucker","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7363-6809","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69931805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"8","first_page":"9431","last_page":"9438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8898000121116638,"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":0.8898000121116638,"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":0.02070000022649765,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.006899999920278788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5670999884605408},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4404999911785126},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3190999925136566},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30640000104904175},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2793999910354614}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5996000170707703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5702999830245972},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5670999884605408},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3700381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3700381","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5305641791","display_name":null,"funder_award_id":"W911NF-19-S-0001","funder_id":"https://openalex.org/F4320338456","funder_display_name":"DEVCOM Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338456","display_name":"DEVCOM Army Research Laboratory","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2911087563","https://openalex.org/W2994446013","https://openalex.org/W3021613070","https://openalex.org/W3036619998","https://openalex.org/W3091627088","https://openalex.org/W3206918183","https://openalex.org/W4287266177","https://openalex.org/W4393147692","https://openalex.org/W4394805110","https://openalex.org/W4401023787","https://openalex.org/W4401414091","https://openalex.org/W4409364052","https://openalex.org/W4412588144","https://openalex.org/W4414079055","https://openalex.org/W4415121671","https://openalex.org/W7133199224"],"related_works":[],"abstract_inverted_index":{"Multi-objective":[0],"reinforcement":[1],"learning":[2,105,123],"(MORL)":[3],"is":[4],"a":[5,63,116],"powerful":[6],"tool":[7],"to":[8,30,91,97],"learn":[9],"Pareto-optimal":[10,124],"policy":[11],"families":[12],"across":[13,127],"conflicting":[14],"objectives.":[15],"However,":[16],"unlike":[17],"traditional":[18],"RL":[19],"algorithms,":[20],"existing":[21],"MORL":[22,49,67],"algorithms":[23],"do":[24],"not":[25],"effectively":[26],"leverage":[27],"large-scale":[28],"parallelization":[29],"concurrently":[31],"simulate":[32],"thousands":[33],"of":[34,48,74],"environments,":[35],"thus":[36],"facing":[37],"vastly":[38],"increased":[39],"computation":[40],"time.":[41],"Ultimately,":[42],"this":[43],"has":[44],"limited":[45],"the":[46],"application":[47],"towards":[50],"complex":[51],"multi-objective":[52,76],"robotics":[53],"problems.":[54],"To":[55],"address":[56],"these":[57],"challenges,":[58],"we":[59],"present":[60],"1)":[61],"MORLAX,":[62],"new":[64],"GPU-native,":[65],"fast":[66],"algorithm,":[68],"and":[69,80,95,122,137],"2)":[70],"MO-Playground,":[71],"apip-installable":[72],"playground":[73],"GPU-accelerated":[75],"environments.":[77],"Together,":[78],"MORLAX":[79],"MO-Playground":[81],"approximate":[82],"Pareto":[83,107],"sets":[84],"within":[85],"minutes,":[86],"offering":[87],"26-271x":[88],"speed-ups":[89,99],"compared":[90],"legacy":[92],"CPU-based":[93],"approaches":[94,103],"up":[96],"19x":[98],"over":[100],"prior":[101],"GPU-based":[102],"whilst":[104],"superior":[106],"front":[108],"hypervolumes.":[109],"We":[110],"demonstrate":[111],"MO-Playground's":[112],"versatility":[113],"by":[114],"implementing":[115],"custom":[117],"BRUCE":[118],"humanoid":[119],"robot":[120],"environment":[121],"locomotion":[125],"policies":[126],"6":[128],"practical":[129],"objectives":[130],"in":[131],"simulation,":[132],"such":[133],"as":[134],"smoothness,":[135],"efficiency":[136],"arm":[138],"swinging.":[139]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-06-05T00:00:00"}