{"id":"https://openalex.org/W4388561956","doi":"https://doi.org/10.1109/icstcc59206.2023.10308465","title":"Learning the Dynamic Environment of an Original Game Using Hierarchical Reinforcement Learning Methods","display_name":"Learning the Dynamic Environment of an Original Game Using Hierarchical Reinforcement Learning Methods","publication_year":2023,"publication_date":"2023-10-11","ids":{"openalex":"https://openalex.org/W4388561956","doi":"https://doi.org/10.1109/icstcc59206.2023.10308465"},"language":"en","primary_location":{"id":"doi:10.1109/icstcc59206.2023.10308465","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icstcc59206.2023.10308465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 27th International Conference on System Theory, Control and Computing (ICSTCC)","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/A5093236395","display_name":"Vlad Batalan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108695","display_name":"Gheorghe Asachi Technical University of Ia\u0219i","ror":"https://ror.org/014zxnz40","country_code":"RO","type":"education","lineage":["https://openalex.org/I4210108695"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Vlad Batalan","raw_affiliation_strings":["“Gheorghe Asachi” Technical University of Iași,Faculty of Automatic Control and Computer Engineering,Iași,Romania"],"affiliations":[{"raw_affiliation_string":"“Gheorghe Asachi” Technical University of Iași,Faculty of Automatic Control and Computer Engineering,Iași,Romania","institution_ids":["https://openalex.org/I4210108695"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063576338","display_name":"Florin Leon","orcid":"https://orcid.org/0000-0002-1370-9145"},"institutions":[{"id":"https://openalex.org/I4210108695","display_name":"Gheorghe Asachi Technical University of Ia\u0219i","ror":"https://ror.org/014zxnz40","country_code":"RO","type":"education","lineage":["https://openalex.org/I4210108695"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Florin Leon","raw_affiliation_strings":["“Gheorghe Asachi” Technical University of Iași,Faculty of Automatic Control and Computer Engineering,Iași,Romania"],"affiliations":[{"raw_affiliation_string":"“Gheorghe Asachi” Technical University of Iași,Faculty of Automatic Control and Computer Engineering,Iași,Romania","institution_ids":["https://openalex.org/I4210108695"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093236395"],"corresponding_institution_ids":["https://openalex.org/I4210108695"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14602489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"422","last_page":"427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9965000152587891,"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":0.9934999942779541,"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/computer-science","display_name":"Computer science","score":0.8845953941345215},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8495807647705078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5383952260017395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49639207124710083},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4949297308921814},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41966307163238525},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4171098470687866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8845953941345215},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8495807647705078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5383952260017395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49639207124710083},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4949297308921814},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41966307163238525},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4171098470687866},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icstcc59206.2023.10308465","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icstcc59206.2023.10308465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 27th International Conference on System Theory, Control and Computing (ICSTCC)","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":13,"referenced_works":["https://openalex.org/W2121517924","https://openalex.org/W2145339207","https://openalex.org/W2539402368","https://openalex.org/W2788477667","https://openalex.org/W2963161674","https://openalex.org/W2995726179","https://openalex.org/W2997510038","https://openalex.org/W3168892396","https://openalex.org/W3190154035","https://openalex.org/W6629152578","https://openalex.org/W6744935223","https://openalex.org/W6764125455","https://openalex.org/W6780287401"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W1585007175","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W2382521049","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W4306904969","https://openalex.org/W2090827041"],"abstract_inverted_index":{"This":[0,115],"paper":[1],"compares":[2],"the":[3,30,33,49,54,63,66,81,84,90,103,107,120,135],"performance":[4,64],"of":[5,22,32,65,74,83,99,124,137],"two":[6],"reinforcement":[7,127],"learning":[8,14,128],"algorithms,":[9],"Q-Learning":[10,56],"and":[11,39,101,122,133,140],"MAXQ-0,":[12],"in":[13,80],"to":[15,77],"play":[16],"an":[17,96],"original":[18],"game.":[19],"An":[20],"extension":[21],"MAXQ-0":[23],"algorithm,":[24],"MAXQ-P":[25,47,67],"is":[26,92,110],"introduced,":[27],"which":[28],"enhances":[29],"variety":[31],"tree":[34],"nodes":[35],"with":[36,95],"simple,":[37],"ordered":[38],"repetitive":[40],"nodes.":[41],"The":[42],"hierarchical":[43,126],"approach":[44,57],"provided":[45],"by":[46],"finds":[48,106],"optimal":[50,145],"solution":[51],"faster":[52],"than":[53],"flat":[55],"but":[58],"converges":[59],"more":[60],"slowly.":[61],"Furthermore,":[62],"algorithm":[68],"decreases":[69],"after":[70],"a":[71],"certain":[72],"number":[73],"episodes":[75],"due":[76],"representation":[78],"error":[79],"weights":[82],"model.":[85],"To":[86],"address":[87],"this":[88],"issue,":[89],"model":[91,104],"periodically":[93],"tested":[94],"exploration":[97],"value":[98],"0,":[100],"if":[102],"successfully":[105],"solution,":[108],"it":[109],"stored":[111],"for":[112,130,144],"future":[113],"use.":[114],"study":[116],"provides":[117],"insights":[118],"into":[119],"benefits":[121],"drawbacks":[123],"using":[125],"algorithms":[129,143],"complex":[131],"tasks":[132],"highlights":[134],"importance":[136],"carefully":[138],"designing":[139],"training":[141],"such":[142],"performance.":[146]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}