{"id":"https://openalex.org/W2975583152","doi":"https://doi.org/10.1109/cig.2019.8848113","title":"Macro and Micro Reinforcement Learning for Playing Nine-ball Pool","display_name":"Macro and Micro Reinforcement Learning for Playing Nine-ball Pool","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2975583152","doi":"https://doi.org/10.1109/cig.2019.8848113","mag":"2975583152"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2019.8848113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2019.8848113","pdf_url":null,"source":{"id":"https://openalex.org/S4306498491","display_name":"2019 IEEE Conference on Games (CoG)","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":"2019 IEEE Conference on Games (CoG)","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/A5100402071","display_name":"Yu Chen","orcid":"https://orcid.org/0000-0002-8118-7262"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Chen","raw_affiliation_strings":["Guanghua School of Management, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Guanghua School of Management, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082725090","display_name":"Yujun Li","orcid":"https://orcid.org/0000-0001-6658-2371"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Li","raw_affiliation_strings":["Guanghua School of Management, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Guanghua School of Management, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100402071"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61285347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"529","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9991999864578247,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9991999864578247,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9925000071525574,"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":0.9322938919067383},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.7840590476989746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7189600467681885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5732445120811462},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5322705507278442},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.5211020708084106},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4279427230358124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42014554142951965},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4190785586833954},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.4173215627670288},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.414596289396286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35615074634552},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15441736578941345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0831000804901123}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9322938919067383},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.7840590476989746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189600467681885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5732445120811462},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5322705507278442},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.5211020708084106},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4279427230358124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42014554142951965},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4190785586833954},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.4173215627670288},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.414596289396286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35615074634552},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15441736578941345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0831000804901123},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cig.2019.8848113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2019.8848113","pdf_url":null,"source":{"id":"https://openalex.org/S4306498491","display_name":"2019 IEEE Conference on Games (CoG)","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":"2019 IEEE Conference on Games (CoG)","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":22,"referenced_works":["https://openalex.org/W113028485","https://openalex.org/W206760003","https://openalex.org/W1501807268","https://openalex.org/W1513765320","https://openalex.org/W1998496300","https://openalex.org/W2150468603","https://openalex.org/W2257979135","https://openalex.org/W2574978968","https://openalex.org/W2730357202","https://openalex.org/W2735170665","https://openalex.org/W2806145634","https://openalex.org/W2963571817","https://openalex.org/W2963871073","https://openalex.org/W2964121744","https://openalex.org/W3103780890","https://openalex.org/W6608373825","https://openalex.org/W6629980402","https://openalex.org/W6631190155","https://openalex.org/W6707268500","https://openalex.org/W6740640171","https://openalex.org/W6740786254","https://openalex.org/W6752211340"],"related_works":["https://openalex.org/W3136325136","https://openalex.org/W2371091044","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W2391666574","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1493952344","https://openalex.org/W4312372616","https://openalex.org/W8539471"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,6,18,50,59,71],"method":[3,99],"of":[4,20,56,67],"training":[5,15],"reinforcement":[7,21,79],"learning":[8,80],"agent":[9,86],"to":[10,45,63,77,103],"play":[11],"nine-ball":[12],"pool.":[13],"The":[14,85],"process":[16],"uses":[17],"combination":[19],"learning,":[22],"deep":[23],"neural":[24],"networks":[25],"and":[26,40,73,81,93],"search":[27,83],"trees.":[28],"These":[29],"technologies":[30],"have":[31,58],"achieved":[32],"tremendous":[33],"results":[34],"in":[35],"discrete":[36],"strategy":[37],"board":[38],"games,":[39,47],"we":[41,69],"extend":[42],"their":[43],"applications":[44],"pool":[46],"which":[48],"is":[49],"complicated":[51],"continuous":[52],"case.":[53],"Pool":[54],"types":[55],"games":[57],"huge":[60],"action":[61,75],"space,":[62],"improve":[64],"the":[65,82,95,101],"efficiency":[66],"exploration,":[68],"use":[70],"macro":[72],"micro":[74],"framework":[76],"combine":[78],"tree.":[84],"learns":[87],"skills":[88],"such":[89],"as":[90],"choosing":[91],"pockets":[92],"control":[94],"post-collision":[96],"position.":[97],"Our":[98],"shows":[100],"potential":[102],"solve":[104],"billiards":[105],"planning":[106],"problems":[107],"through":[108],"AI.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}