{"id":"https://openalex.org/W4413945285","doi":"https://doi.org/10.1109/icra55743.2025.11128707","title":"Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer","display_name":"Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945285","doi":"https://doi.org/10.1109/icra55743.2025.11128707"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5034888443","display_name":"Adam Labiosa","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adam Labiosa","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109704683","display_name":"Zhihan Wang","orcid":"https://orcid.org/0009-0002-7085-8996"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihan Wang","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069875677","display_name":"Siddhant Agarwal","orcid":"https://orcid.org/0000-0002-0840-2114"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhant Agarwal","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002629143","display_name":"Wenxiang Cong","orcid":"https://orcid.org/0000-0003-2908-1759"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Cong","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092010501","display_name":"Geethika Hemkumar","orcid":"https://orcid.org/0000-0002-1021-6580"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geethika Hemkumar","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008720605","display_name":"Abhinav Narayan Harish","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Narayan Harish","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088719128","display_name":"Bo Hong","orcid":"https://orcid.org/0000-0003-2900-6791"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Hong","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075376744","display_name":"Josh Kelle","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh Kelle","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379280","display_name":"Li Chen","orcid":"https://orcid.org/0000-0002-8120-5758"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101839686","display_name":"Yuhao Li","orcid":"https://orcid.org/0009-0007-1327-9046"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhao Li","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089489410","display_name":"Zisen Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zisen Shao","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008014974","display_name":"Josiah P. Hanna","orcid":"https://orcid.org/0000-0002-7411-0398"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josiah P. Hanna","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5034888443"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13527619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14999","last_page":"15006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.928600013256073,"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":0.928600013256073,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8547457456588745},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.711808443069458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7043889164924622},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5948629379272461},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.5942417979240417},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5572383403778076},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48874783515930176},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4861471354961395},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3446560502052307},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33675524592399597},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.27195337414741516},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05371996760368347},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.04432263970375061}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8547457456588745},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.711808443069458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7043889164924622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5948629379272461},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.5942417979240417},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5572383403778076},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48874783515930176},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4861471354961395},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3446560502052307},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33675524592399597},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27195337414741516},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05371996760368347},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.04432263970375061}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":33,"referenced_works":["https://openalex.org/W1483079495","https://openalex.org/W2034587361","https://openalex.org/W2042520683","https://openalex.org/W2095182442","https://openalex.org/W2104641222","https://openalex.org/W2127412976","https://openalex.org/W2204090322","https://openalex.org/W2968717280","https://openalex.org/W3016463908","https://openalex.org/W3038194455","https://openalex.org/W3091304796","https://openalex.org/W3134918303","https://openalex.org/W3138971305","https://openalex.org/W3158362201","https://openalex.org/W3164631379","https://openalex.org/W3174857949","https://openalex.org/W3199351557","https://openalex.org/W3206620955","https://openalex.org/W3213426571","https://openalex.org/W4212766024","https://openalex.org/W4235195725","https://openalex.org/W4312908419","https://openalex.org/W4322724518","https://openalex.org/W4360825542","https://openalex.org/W4383108493","https://openalex.org/W4385781536","https://openalex.org/W4389665855","https://openalex.org/W4394674699","https://openalex.org/W4399284119","https://openalex.org/W4401416668","https://openalex.org/W4409348659","https://openalex.org/W4411328628","https://openalex.org/W4413435736"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W4220829754","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"Robot":[0],"decision-making":[1],"in":[2,27,33,43,83],"partially":[3],"observable,":[4],"real-time,":[5],"dynamic,":[6],"and":[7,13,69,100],"multi-agent":[8],"environments":[9,35],"remains":[10],"a":[11,21,53,59,65],"difficult":[12],"unsolved":[14],"challenge.":[15],"Model-free":[16],"reinforcement":[17],"learning":[18,25],"(RL)":[19],"is":[20,36],"promising":[22],"approach":[23,68,112],"to":[24,81,108],"decisionmaking":[26],"such":[28],"domains,":[29],"however,":[30],"end-to-end":[31],"RL":[32,57],"complex":[34],"often":[37],"intractable.":[38],"To":[39],"address":[40],"this":[41,92],"challenge":[42],"the":[44,84],"RoboCup":[45,86],"Standard":[46],"Platform":[47],"League":[48],"(SPL)":[49],"domain,":[50],"we":[51,94],"developed":[52],"novel":[54],"architecture":[55,79,99],"integrating":[56],"within":[58],"classical":[60],"robotics":[61],"stack,":[62],"while":[63],"employing":[64],"multi-fidelity":[66],"sim2real":[67],"decomposing":[70],"behavior":[71,123],"into":[72,120],"learned":[73],"sub-behaviors":[74],"with":[75],"heuristic":[76],"selection.":[77],"Our":[78,111],"led":[80],"victory":[82],"2024":[85],"SPL":[87],"Challenge":[88],"Shield":[89],"Division.":[90],"In":[91],"work,":[93],"fully":[95],"describe":[96],"our":[97],"system's":[98],"empirically":[101],"analyze":[102],"key":[103],"design":[104],"decisions":[105],"that":[106],"contributed":[107],"its":[109],"success.":[110],"demonstrates":[113],"how":[114],"RL-based":[115],"behaviors":[116],"can":[117],"be":[118],"integrated":[119],"complete":[121],"robot":[122],"architectures.":[124]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
