{"id":"https://openalex.org/W4206377728","doi":"https://doi.org/10.1109/cog52621.2021.9619104","title":"Inventory Management with Attention-Based Meta Actions","display_name":"Inventory Management with Attention-Based Meta Actions","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W4206377728","doi":"https://doi.org/10.1109/cog52621.2021.9619104"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9619104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619104","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 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":"2021 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/A5065830501","display_name":"Keisuke Izumiya","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Keisuke Izumiya","raw_affiliation_strings":["Waseda University,Department of Computer Science and Communications Engineering,Tokyo,Japan","Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Computer Science and Communications Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061430475","display_name":"Edgar Simo\u2010Serra","orcid":"https://orcid.org/0000-0003-2544-8592"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Edgar Simo-Serra","raw_affiliation_strings":["Waseda University,Department of Computer Science and Communications Engineering,Tokyo,Japan","Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Computer Science and Communications Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065830501"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19900916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9965000152587891,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9883999824523926,"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":0.8281051516532898},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.788477897644043},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6673204302787781},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6543310880661011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6483728289604187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5787830352783203},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5320765972137451},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42847999930381775},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07692825794219971}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281051516532898},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.788477897644043},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6673204302787781},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6543310880661011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6483728289604187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5787830352783203},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5320765972137451},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42847999930381775},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07692825794219971},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog52621.2021.9619104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619104","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 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":"2021 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1714211023","https://openalex.org/W2150468603","https://openalex.org/W2257979135","https://openalex.org/W2756674674","https://openalex.org/W2766480765","https://openalex.org/W2784604269","https://openalex.org/W2798925270","https://openalex.org/W2907502844","https://openalex.org/W2913906356","https://openalex.org/W2941355526","https://openalex.org/W2949847915","https://openalex.org/W2950872548","https://openalex.org/W2963095800","https://openalex.org/W2964043796","https://openalex.org/W2964067469","https://openalex.org/W2966576392","https://openalex.org/W2975112661","https://openalex.org/W2980077985","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2996037775","https://openalex.org/W3004997297","https://openalex.org/W3034885317","https://openalex.org/W3037871539","https://openalex.org/W3094013182","https://openalex.org/W3118210634","https://openalex.org/W4297797010","https://openalex.org/W4298857966","https://openalex.org/W4385245566","https://openalex.org/W6637441126","https://openalex.org/W6637967152","https://openalex.org/W6692846177","https://openalex.org/W6729556111","https://openalex.org/W6730111887","https://openalex.org/W6732958910","https://openalex.org/W6739901393","https://openalex.org/W6744343907","https://openalex.org/W6745026974","https://openalex.org/W6747520938","https://openalex.org/W6748638692","https://openalex.org/W6756303580","https://openalex.org/W6757797181","https://openalex.org/W6761839350","https://openalex.org/W6772005887","https://openalex.org/W6773716603","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Roguelike":[0],"games":[1],"are":[2,81],"a":[3,75,91,147,157],"challenging":[4,52,166],"environment":[5],"for":[6,43],"Reinforcement":[7],"Learning":[8],"(RL)":[9],"algorithms":[10,45],"due":[11],"to":[12,14,34,49,54,107,178],"having":[13,122],"restart":[15],"the":[16,19,55,64,67,100,119,128,165],"game":[17,167],"from":[18],"beginning":[20],"when":[21],"losing,":[22],"randomized":[23],"procedural":[24],"generation,":[25],"and":[26,46,80,131,139,154,161],"proper":[27],"use":[28],"of":[29,57,71,94,99,121,127,168],"in-game":[30],"items":[31,155],"being":[32,86],"essential":[33],"success.":[35],"While":[36],"recent":[37],"research":[38],"has":[39],"proposed":[40,47],"roguelike":[41],"environments":[42],"RL":[44,112],"models":[48],"handle":[50,151],"this":[51,115],"task,":[53],"best":[56],"our":[58,174],"knowledge,":[59],"none":[60],"have":[61],"dealt":[62],"with":[63,90,141],"elephant":[65],"in":[66,78],"room,":[68],"i.e.,":[69],"handling":[70],"items.":[72],"Items":[73],"play":[74],"fundamental":[76],"role":[77],"roguelikes":[79],"acquired":[82],"during":[83],"gameplay.":[84],"However,":[85],"an":[87,111,133],"unordered":[88,123],"set":[89],"non-fixed":[92],"amount":[93],"elements":[95],"which":[96],"form":[97],"part":[98,126],"action":[101,129,159],"space,":[102],"it":[103],"is":[104,176],"not":[105],"straightforward":[106],"incorporate":[108],"them":[109,163],"into":[110],"framework.":[113],"In":[114],"work,":[116],"we":[117],"tackle":[118],"issue":[120],"sets":[124],"be":[125],"space":[130],"propose":[132,146],"attention-based":[134],"mechanism":[135],"that":[136,149,173],"can":[137,150],"select":[138],"deal":[140],"item-based":[142],"actions.":[143],"We":[144],"also":[145],"model":[148],"complex":[152],"actions":[153],"through":[156],"meta":[158],"framework":[160],"evaluate":[162],"on":[164],"NetHack.":[169],"Experimental":[170],"results":[171],"show":[172],"approach":[175],"able":[177],"significantly":[179],"outperform":[180],"existing":[181],"approaches.":[182]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}