{"id":"https://openalex.org/W4385242008","doi":"https://doi.org/10.1007/978-3-031-37649-8_5","title":"Representation of\u00a0Observations in\u00a0Reinforcement Learning for\u00a0Playing Arcade Fighting Game","display_name":"Representation of\u00a0Observations in\u00a0Reinforcement Learning for\u00a0Playing Arcade Fighting Game","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385242008","doi":"https://doi.org/10.1007/978-3-031-37649-8_5"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-37649-8_5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-37649-8_5","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-37649-8_5.pdf","source":{"id":"https://openalex.org/S4210169156","display_name":"Lecture notes in networks and systems","issn_l":"2367-3370","issn":["2367-3370","2367-3389"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Networks and Systems","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-37649-8_5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005081887","display_name":"Huaiyu Du","orcid":"https://orcid.org/0000-0002-6160-8330"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Huaiyu Du","raw_affiliation_strings":["Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0002-6160-8330","affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080338584","display_name":"Rafa\u0142 J\u00f3\u017awiak","orcid":"https://orcid.org/0000-0003-0753-7241"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]},{"id":"https://openalex.org/I4210139285","display_name":"National Information Processing Institute","ror":"https://ror.org/040fc1e14","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210139285"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Rafa\u0142 J\u00f3\u017awiak","raw_affiliation_strings":["Applied Artificial Intelligence Laboratory, National Information Processing Institute, Warsaw, Poland","Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0003-0753-7241","affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Laboratory, National Information Processing Institute, Warsaw, Poland","institution_ids":["https://openalex.org/I4210139285"]},{"raw_affiliation_string":"Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland","institution_ids":["https://openalex.org/I108403487"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005081887"],"corresponding_institution_ids":["https://openalex.org/I108403487"],"apc_list":null,"apc_paid":null,"fwci":0.5202,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65444365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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/T11197","display_name":"Digital Games and Media","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8088484406471252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7118164300918579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6295751333236694},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.579494059085846},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5586444735527039},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5260764956474304},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4884406626224518},{"id":"https://openalex.org/keywords/video-game","display_name":"Video game","score":0.4576714038848877},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4234773516654968},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13814309239387512},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09486585855484009}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8088484406471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7118164300918579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6295751333236694},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.579494059085846},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5586444735527039},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5260764956474304},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4884406626224518},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.4576714038848877},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4234773516654968},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13814309239387512},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09486585855484009},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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:10.1007/978-3-031-37649-8_5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-37649-8_5","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-37649-8_5.pdf","source":{"id":"https://openalex.org/S4210169156","display_name":"Lecture notes in networks and systems","issn_l":"2367-3370","issn":["2367-3370","2367-3389"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Networks and Systems","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-37649-8_5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-37649-8_5","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-37649-8_5.pdf","source":{"id":"https://openalex.org/S4210169156","display_name":"Lecture notes in networks and systems","issn_l":"2367-3370","issn":["2367-3370","2367-3389"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Networks and Systems","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385242008.pdf"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2962693466","https://openalex.org/W2982316857","https://openalex.org/W3094607870","https://openalex.org/W3118881636","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W1503216044","https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W2366269494","https://openalex.org/W2353650902","https://openalex.org/W2347884623","https://openalex.org/W2159790760"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1,18],"learning":[2,10,14,19],"(RL)":[3],"is":[4,89],"one":[5],"of":[6,45,48,60,70,74,77,95,117,137,204],"three":[7],"basic":[8,185],"machine":[9],"paradigms,":[11],"alongside":[12],"supervised":[13],"and":[15,29,33,62,153,160,187],"unsupervised":[16],"learning.":[17],"algorithms":[20],"have":[21],"become":[22],"very":[23],"popular":[24],"in":[25],"simple":[26],"computer":[27],"games":[28,30,40],"like":[31],"chess":[32],"GO.":[34],"However,":[35],"playing":[36],"classical":[37],"arcade":[38],"fighting":[39],"would":[41],"be":[42],"challenging":[43],"because":[44],"the":[46,49,58,84,93,96,103,106,115,125,135,150,163,171,178,181,191,201,208],"complexity":[47],"command":[50],"system":[51],"(the":[52],"character":[53],"makes":[54],"moves":[55,189],"according":[56],"to":[57,101,129,197],"sequence":[59,136],"input)":[61],"combo":[63],"system.":[64],"In":[65,177],"this":[66],"paper,":[67],"a":[68,71,131,144],"creation":[69],"game":[72],"environment":[73],"The":[75,120],"King":[76],"Fighters":[78],"\u201997":[79],"(KOF":[80],"\u201997),":[81],"which":[82,113,156],"implements":[83],"open":[85],"gym":[86],"env":[87],"interface,":[88],"described.":[90],"Based":[91],"on":[92,170],"characteristics":[94],"game,":[97],"an":[98],"innovative":[99],"approach":[100],"represent":[102],"observations":[104,121],"from":[105,140],"last":[107],"few":[108],"steps":[109,142],"has":[110],"been":[111],"proposed,":[112],"guarantees":[114],"preservation":[116],"Markov\u2019s":[118],"property.":[119],"are":[122,157],"coded":[123],"using":[124,200],"\u201cone-hot":[126],"encoding\u201d":[127],"technique":[128],"form":[130],"binary":[132,145],"vector,":[133],"while":[134],"stacked":[138],"vectors":[139],"successive":[141],"creates":[143],"image.":[146],"This":[147],"image":[148],"encodes":[149],"character\u2019s":[151],"input":[152],"behavioural":[154],"pattern,":[155],"then":[158],"retrieved":[159],"recognized":[161],"by":[162],"CNN":[164],"network.":[165],"A":[166],"network":[167,174],"structure":[168],"based":[169],"Advantage":[172],"Actor-Critic":[173],"was":[175,195],"proposed.":[176],"experimental":[179],"verification,":[180],"RL":[182],"agent":[183],"performing":[184],"combos":[186],"complex":[188],"(including":[190],"so-called":[192],"\u201cdesperation":[193],"moves\u201d)":[194],"able":[196],"defeat":[198],"characters":[199],"highest":[202],"level":[203],"AI":[205],"built":[206],"into":[207],"game.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}