{"id":"https://openalex.org/W4248496491","doi":"https://doi.org/10.1109/icsmc.2003.1243791","title":"Progress in learning 3 vs. 2 keepaway","display_name":"Progress in learning 3 vs. 2 keepaway","publication_year":2004,"publication_date":"2004-06-22","ids":{"openalex":"https://openalex.org/W4248496491","doi":"https://doi.org/10.1109/icsmc.2003.1243791"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2003.1243791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2003.1243791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483)","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/A5080436382","display_name":"G. Kuhlmann","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":"G. Kuhlmann","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008920280","display_name":"P. Stone","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":"P. Stone","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.2205,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.53181993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"52","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.948199987411499,"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":0.948199987411499,"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":0.01269999984651804,"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":0.007499999832361937,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9160114526748657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7444266676902771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6271327137947083},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5563976764678955},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4740692675113678},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46809935569763184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45120298862457275},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4457019865512848},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4388169050216675},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09600770473480225},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07020682096481323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.061510711908340454}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9160114526748657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444266676902771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6271327137947083},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5563976764678955},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4740692675113678},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46809935569763184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45120298862457275},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4457019865512848},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4388169050216675},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09600770473480225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07020682096481323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.061510711908340454},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2003.1243791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2003.1243791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W123412229","https://openalex.org/W1495978126","https://openalex.org/W1506497862","https://openalex.org/W1585603966","https://openalex.org/W1747702904","https://openalex.org/W1815493548","https://openalex.org/W2130985368","https://openalex.org/W2153947321","https://openalex.org/W2155791599","https://openalex.org/W2156662806","https://openalex.org/W2171181350","https://openalex.org/W6605076657","https://openalex.org/W6630231469","https://openalex.org/W6635049011","https://openalex.org/W6682802936","https://openalex.org/W6683164292"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W3021988786","https://openalex.org/W3099311996","https://openalex.org/W2963971282"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,115],"has":[2,27],"been":[3,28,95],"successfully":[4],"applied":[5],"to":[6,60,76,90,116],"several":[7,121],"subtasks":[8],"in":[9,23,79],"the":[10,24,29,45,53,61,72,80,109,125],"RoboCup":[11,117],"simulated":[12],"soccer":[13],"domain.":[14],"Keepaway":[15],"is":[16,104],"one":[17],"such":[18],"task.":[19],"One":[20],"notable":[21],"success":[22,41],"keepaway":[25],"domain":[26],"application":[30],"of":[31,47,55,82,101,108,111],"SMDP":[32],"Sarsa(/spl":[33],"lambda/)":[34],"with":[35,44,128],"tile-coding":[36],"function":[37],"approximation.":[38],"However,":[39],"this":[40,67,102],"was":[42,70],"achieved":[43],"help":[46],"some":[48],"significant":[49],"task":[50,68],"simplifications,":[51],"including":[52],"delivery":[54],"complete,":[56],"noise-free":[57],"world-state":[58],"information":[59],"agents.":[62],"Here":[63],"we":[64],"demonstrate":[65],"that":[66],"simplification":[69],"unnecessary:":[71],"agents":[73],"are":[74],"able":[75],"learn":[77],"even":[78],"presence":[81],"noisy,":[83],"incomplete":[84],"information.":[85],"We":[86,119],"also":[87],"scale":[88],"up":[89,113],"larger":[91],"problems":[92],"than":[93],"have":[94],"previously":[96],"tried.":[97],"The":[98],"main":[99],"contribution":[100],"paper":[103],"a":[105],"deeper":[106],"understanding":[107],"difficulties":[110],"scaling":[112],"reinforcement":[114],"soccer.":[118],"address":[120],"focused":[122],"questions":[123],"about":[124],"previous":[126],"results":[127],"detailed":[129],"experiments.":[130]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}