{"id":"https://openalex.org/W4393256777","doi":"https://doi.org/10.1142/s1793351x24430025","title":"Optimization of 2D Irregular Packing: Deep Reinforcement Learning with Dense Reward","display_name":"Optimization of 2D Irregular Packing: Deep Reinforcement Learning with Dense Reward","publication_year":2024,"publication_date":"2024-03-28","ids":{"openalex":"https://openalex.org/W4393256777","doi":"https://doi.org/10.1142/s1793351x24430025"},"language":"en","primary_location":{"id":"doi:10.1142/s1793351x24430025","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x24430025","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-7108","issn":["1793-7108","1793-351X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-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":null,"display_name":"Viviana Crescitelli","orcid":"https://orcid.org/0009-0004-9540-4514"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Viviana Crescitelli","raw_affiliation_strings":["Research and Development Group, Hitachi Ltd., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0004-9540-4514","affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036668422","display_name":"T. Oshima","orcid":"https://orcid.org/0000-0002-1069-3221"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Oshima","raw_affiliation_strings":["Research and Development Group, Hitachi Ltd., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1069-3221","affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":0.2185,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51990566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"18","issue":"03","first_page":"405","last_page":"416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12176","display_name":"Optimization and Packing Problems","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12176","display_name":"Optimization and Packing Problems","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12782","display_name":"Assembly Line Balancing Optimization","score":0.9426000118255615,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.8478135466575623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.807611346244812},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6150587201118469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48253342509269714},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.08770999312400818},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07550707459449768}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8478135466575623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807611346244812},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6150587201118469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48253342509269714},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.08770999312400818},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07550707459449768}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1793351x24430025","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x24430025","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-7108","issn":["1793-7108","1793-351X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1982458653","https://openalex.org/W1997959089","https://openalex.org/W1998094432","https://openalex.org/W2017204313","https://openalex.org/W2027852719","https://openalex.org/W2105175235","https://openalex.org/W2158380317","https://openalex.org/W2570651606","https://openalex.org/W2746553466","https://openalex.org/W2956161617","https://openalex.org/W2963544079","https://openalex.org/W3091677803","https://openalex.org/W3199412365","https://openalex.org/W3206745158","https://openalex.org/W3211449378","https://openalex.org/W3215436229","https://openalex.org/W4214717370","https://openalex.org/W4292448915","https://openalex.org/W4317243109","https://openalex.org/W4376624717","https://openalex.org/W4390905849"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291"],"abstract_inverted_index":{"This":[0,134],"paper":[1],"introduces":[2,45],"a":[3,23,33,46,70],"method":[4,21,44],"to":[5,27,68,73,99],"solve":[6],"the":[7,29,65,75,87,93,115,120,141,160],"2D":[8,76,122,151],"irregular":[9,77,123,152],"packing":[10,52,78,124,153],"problem":[11],"using":[12],"Deep":[13,40,95],"Reinforcement":[14],"Learning":[15],"(Deep":[16],"RL)":[17],"for":[18,170],"logistics.":[19],"Our":[20],"employs":[22],"Q":[24],"agent":[25],"trained":[26],"predict":[28],"best":[30],"placement":[31],"within":[32],"container,":[34],"maximizing":[35],"available":[36],"space.":[37],"Unlike":[38],"previous":[39],"RL":[41],"algorithms,":[42],"our":[43,61,82,101,137],"dense":[47,71,147],"reward":[48,72,148],"function":[49],"at":[50],"each":[51],"step,":[53],"providing":[54],"immediate":[55],"feedback":[56],"and":[57,108,130,146],"accelerating":[58],"learning.":[59],"To":[60],"knowledge,":[62],"this":[63],"is":[64],"first":[66],"approach":[67],"use":[69],"address":[74],"problem.":[79],"Building":[80],"on":[81],"earlier":[83],"work,":[84],"we":[85],"improve":[86],"deep":[88,102,163],"neural":[89],"network":[90],"by":[91],"incorporating":[92],"Double":[94],"Q-Network":[96],"(DDQN)":[97],"framework":[98],"enhance":[100],"Q-learning":[103],"approach,":[104],"reducing":[105],"overestimation":[106],"biases":[107],"improving":[109],"decision-making":[110],"reliability.":[111],"Simulation":[112],"results":[113],"show":[114],"method\u2019s":[116],"effectiveness":[117],"in":[118,149],"completing":[119],"online":[121],"tasks,":[125],"achieving":[126],"promising":[127],"volume":[128],"efficiency":[129],"packed":[131],"piece":[132],"metrics.":[133],"research":[135],"extends":[136],"initial":[138],"findings,":[139],"highlighting":[140],"practical":[142,168],"importance":[143,169],"of":[144,162],"DDQN":[145],"advancing":[150],"problem-solving.":[154],"These":[155],"advancements":[156],"not":[157],"only":[158],"broaden":[159],"applications":[161],"learning":[164],"but":[165],"also":[166],"hold":[167],"real-world":[171],"logistics":[172],"challenges.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}