{"id":"https://openalex.org/W7130541942","doi":"https://doi.org/10.1109/ictc66702.2025.11388216","title":"Generalized Self-Play Reinforcement Learning for Othello under Dynamic Board Constraints","display_name":"Generalized Self-Play Reinforcement Learning for Othello under Dynamic Board Constraints","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130541942","doi":"https://doi.org/10.1109/ictc66702.2025.11388216"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","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":null,"display_name":"Byeongchang Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeongchang Kim","raw_affiliation_strings":["Gwangju Institute of Science and Technology,Department of AI Convergence,Gwangju Metropolitan City,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology,Department of AI Convergence,Gwangju Metropolitan City,Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087777740","display_name":"Y. L. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeaeun Lee","raw_affiliation_strings":["Gwangju Institute of Science and Technology,Department of Electrical Engineering and Computer Science,Gwangju Metropolitan City,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology,Department of Electrical Engineering and Computer Science,Gwangju Metropolitan City,Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006486439","display_name":"Euiseok Hwang","orcid":"https://orcid.org/0000-0002-1718-7030"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Euiseok Hwang","raw_affiliation_strings":["Gwangju Institute of Science and Technology,Department of Electrical Engineering and Computer Science,Gwangju Metropolitan City,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology,Department of Electrical Engineering and Computer Science,Gwangju Metropolitan City,Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8044999837875366,"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":0.8044999837875366,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.12630000710487366,"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":0.011599999852478504,"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":0.7128000259399414},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6061000227928162},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5281999707221985},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.49480000138282776},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4803999960422516},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.47029998898506165},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.43149998784065247}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7128000259399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6320000290870667},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6061000227928162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.54339998960495},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5281999707221985},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.49480000138282776},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C3018963415","wikidata":"https://www.wikidata.org/wiki/Q16878425","display_name":"On board","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7037034630775452,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2769575776","https://openalex.org/W2902907165","https://openalex.org/W2989847975"],"related_works":[],"abstract_inverted_index":{"This":[0],"research":[1],"presents":[2],"a":[3,34,53,69,80],"self-play":[4],"reinforcement":[5],"learning":[6],"framework":[7],"for":[8,46,79],"the":[9,77],"game":[10],"of":[11],"Othello,":[12],"enabling":[13],"generalization":[14],"across":[15],"diverse":[16],"board":[17,23,55],"constraints.":[18],"These":[19],"constraints":[20],"include":[21],"variable":[22],"sizes,":[24],"blocked":[25],"cells,":[26],"and":[27,39],"total":[28],"inference":[29],"time":[30],"limitations.":[31],"FastOthelloNet":[32,64],"incorporates":[33],"lightweight":[35],"convolutional":[36],"input":[37],"architecture":[38],"employs":[40],"Monte":[41],"Carlo":[42],"Tree":[43],"Search":[44],"(MCTS)":[45],"efficient":[47],"planning.":[48],"Unlike":[49],"AlphaZero,":[50],"which":[51,59],"assumes":[52],"fixed":[54],"structure,":[56],"or":[57],"MuZero,":[58],"explicitly":[60],"models":[61],"latent":[62],"dynamics,":[63],"is":[65],"trained":[66],"directly":[67],"on":[68],"randomized":[70],"Othello":[71],"environment":[72],"with":[73],"dynamic":[74],"constraints,":[75],"eliminating":[76],"need":[78],"complex":[81],"world":[82],"model.":[83]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}