{"id":"https://openalex.org/W7124296973","doi":"https://doi.org/10.65109/kuuf3680","title":"Accelerating Neural MCTS Algorithms using Neural Sub-Net Structures","display_name":"Accelerating Neural MCTS Algorithms using Neural Sub-Net Structures","publication_year":2023,"publication_date":"2023-05-30","ids":{"openalex":"https://openalex.org/W7124296973","doi":"https://doi.org/10.65109/kuuf3680"},"language":"en","primary_location":{"id":"doi:10.65109/kuuf3680","doi":"https://doi.org/10.65109/kuuf3680","is_oa":false,"landing_page_url":"https://doi.org/10.65109/kuuf3680","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5024819776","display_name":"Prashank Kadam","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prashank Kadam","raw_affiliation_strings":["Vesta Corporation, Portland, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vesta Corporation, Portland, OR, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023357082","display_name":"Ruiyang Xu","orcid":"https://orcid.org/0000-0002-4973-8458","observed_orcids":["https://orcid.org/0000-0002-4973-8458","https://orcid.org/0009-0008-0409-1970"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruiyang Xu","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077724737","display_name":"Karl J. Lieberherr","orcid":"https://orcid.org/0000-0002-1158-0413","observed_orcids":["https://orcid.org/0000-0002-1158-0413"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karl Lieberherr","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2637","last_page":"2639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.975600004196167,"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":0.975600004196167,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.02370000071823597,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/step-functions","display_name":"step functions","score":0.5740000009536743},{"id":"https://openalex.org/keywords/training-time-reduction","display_name":"training time reduction","score":0.781000018119812},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.8600000143051147},{"id":"https://openalex.org/keywords/self-play-reinforcement-learning","display_name":"self-play reinforcement learning","score":0.6880000233650208}],"concepts":[{"id":"https://openalex.org/C21099817","wikidata":"https://www.wikidata.org/wiki/Q7631721","display_name":"Subnet","level":2,"score":0.8578000068664551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027999997138977},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6965000033378601},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6151000261306763},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46700000762939453},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.65109/kuuf3680","doi":"https://doi.org/10.65109/kuuf3680","is_oa":false,"landing_page_url":"https://doi.org/10.65109/kuuf3680","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3138808933","https://openalex.org/W7221395726","https://openalex.org/W7124285237","https://openalex.org/W7160907541","https://openalex.org/W4387559886","https://openalex.org/W7133246742","https://openalex.org/W7119071835","https://openalex.org/W7210286671","https://openalex.org/W4392945591","https://openalex.org/W2789108549"],"abstract_inverted_index":{"Neural":[0,8,73,113,153],"MCTS":[1,74,114,154],"algorithms":[2,28,43,115,150],"are":[3],"a":[4,24,49,79,90,94,140],"combination":[5],"of":[6,87],"Deep":[7],"Networks":[9],"and":[10,16,59,121,138],"Monte":[11],"Carlo":[12],"Tree":[13],"Search":[14],"(MCTS)":[15],"have":[17,29,44],"successfully":[18],"trained":[19],"Reinforcement":[20],"Learning":[21],"agents":[22],"in":[23,134,151],"tabula-rasa":[25],"way.":[26],"These":[27],"been":[30],"able":[31],"to":[32,52,71,103,119,127,131,145],"find":[33],"near-optimal":[34],"strategies":[35],"through":[36],"self-play":[37],"for":[38,66,96],"different":[39],"problems.":[40],"However,":[41],"these":[42],"significant":[45],"drawbacks;":[46],"they":[47],"take":[48],"long":[50],"time":[51],"converge,":[53],"which":[54,88],"requires":[55],"high":[56],"computational":[57],"power":[58],"electrical":[60],"energy.":[61],"It":[62],"also":[63],"becomes":[64],"difficult":[65],"researchers":[67],"without":[68],"cutting-edge":[69],"hardware":[70],"pursue":[72],"research.":[75],"We":[76,109],"propose":[77],"Step-MCTS,":[78],"novel":[80],"algorithm":[81],"that":[82,92],"uses":[83],"subnet":[84,107],"structures,":[85],"each":[86],"simulates":[89],"tree":[91],"provides":[93],"lookahead":[95],"exploration.":[97],"A":[98],"Step":[99],"function":[100],"is":[101],"used":[102,149],"switch":[104],"between":[105],"the":[106,135,146,152],"structures.":[108],"show":[110,129],"how":[111],"state-of-the-art":[112],"can":[116],"be":[117],"extended":[118,126],"Step-MCTS":[120,128],"evaluate":[122],"their":[123],"performances.":[124],"Algorithms":[125],"up":[130],"~2.1x":[132],"decrease":[133],"training":[136],"times":[137],"achieve":[139],"faster":[141],"convergence":[142],"rate":[143],"compared":[144],"other":[147],"widely":[148],"domain.":[155]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-16T00:00:00"}