{"id":"https://openalex.org/W4401212881","doi":"https://doi.org/10.1145/3653876.3653899","title":"Deep Reinforcement Learning with Swin Transformers","display_name":"Deep Reinforcement Learning with Swin Transformers","publication_year":2024,"publication_date":"2024-02-23","ids":{"openalex":"https://openalex.org/W4401212881","doi":"https://doi.org/10.1145/3653876.3653899"},"language":"en","primary_location":{"id":"doi:10.1145/3653876.3653899","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3653876.3653899","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Digital Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3653876.3653899","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048689963","display_name":"Li Meng","orcid":"https://orcid.org/0000-0002-8867-9104"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Li Meng","raw_affiliation_strings":["Department of Technology Systems, University of Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-8867-9104","affiliations":[{"raw_affiliation_string":"Department of Technology Systems, University of Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002394922","display_name":"Morten Goodwin","orcid":"https://orcid.org/0000-0001-6331-702X"},"institutions":[{"id":"https://openalex.org/I200650556","display_name":"University of Agder","ror":"https://ror.org/03x297z98","country_code":"NO","type":"education","lineage":["https://openalex.org/I200650556"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Morten Goodwin","raw_affiliation_strings":["Centre for Artificial Intelligence Research, University of Agder, Norway"],"raw_orcid":"https://orcid.org/0000-0001-6331-702X","affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Research, University of Agder, Norway","institution_ids":["https://openalex.org/I200650556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032770006","display_name":"Anis Yazidi","orcid":"https://orcid.org/0000-0001-7591-1659"},"institutions":[{"id":"https://openalex.org/I184531372","display_name":"OsloMet \u2013 Oslo Metropolitan University","ror":"https://ror.org/04q12yn84","country_code":"NO","type":"education","lineage":["https://openalex.org/I184531372"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Anis Yazidi","raw_affiliation_strings":["Oslo Metropolitan University, Norway"],"raw_orcid":"https://orcid.org/0000-0001-7591-1659","affiliations":[{"raw_affiliation_string":"Oslo Metropolitan University, Norway","institution_ids":["https://openalex.org/I184531372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090446312","display_name":"Paal Engelstad","orcid":"https://orcid.org/0009-0000-8371-927X"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Paal Engelstad","raw_affiliation_strings":["Department of Technology Systems, University of Oslo, Norway"],"raw_orcid":"https://orcid.org/0009-0000-8371-927X","affiliations":[{"raw_affiliation_string":"Department of Technology Systems, University of Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048689963"],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":null,"apc_paid":null,"fwci":0.9934,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79781054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"205","last_page":"211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983000159263611,"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/T12676","display_name":"Machine Learning and ELM","score":0.9932000041007996,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6311532258987427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5915575623512268},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5725197196006775},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4165671467781067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3905741274356842},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.24528765678405762},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19223976135253906},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07367706298828125},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07019010186195374}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6311532258987427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5915575623512268},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5725197196006775},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4165671467781067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3905741274356842},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.24528765678405762},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19223976135253906},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07367706298828125},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07019010186195374}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3653876.3653899","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3653876.3653899","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Digital Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3653876.3653899","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3653876.3653899","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Digital Signal Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2914643958","https://openalex.org/W3035524453","https://openalex.org/W3048650747","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3193482276","https://openalex.org/W4286611262","https://openalex.org/W4293228258","https://openalex.org/W4366547532","https://openalex.org/W4367662888","https://openalex.org/W4388235249","https://openalex.org/W4399418577","https://openalex.org/W6600721014","https://openalex.org/W6639213019","https://openalex.org/W6702643116","https://openalex.org/W6784601920"],"related_works":["https://openalex.org/W4391375266","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"],"abstract_inverted_index":{"Transformers":[0,38,47],"are":[1],"neural":[2],"network":[3],"models":[4],"that":[5,74,107],"utilize":[6],"multiple":[7],"layers":[8],"of":[9,33,122,141],"self-attention":[10],"heads":[11],"and":[12,39,130],"have":[13,24],"exhibited":[14],"enormous":[15],"potential":[16],"in":[17,99,120,139],"natural":[18],"language":[19],"processing":[20],"tasks.":[21],"Meanwhile,":[22],"there":[23],"been":[25],"efforts":[26],"to":[27,30,60,84],"adapt":[28],"transformers":[29],"visual":[31],"tasks":[32],"machine":[34],"learning,":[35],"including":[36],"Vision":[37,46],"Swin":[40,78,80],"Transformers.":[41],"Although":[42],"some":[43],"researchers":[44],"use":[45],"for":[48],"reinforcement":[49,71],"learning":[50,72],"tasks,":[51],"their":[52],"experiments":[53,95],"remain":[54],"at":[55],"a":[56],"small":[57],"scale":[58],"due":[59],"the":[61,68,91,100,117,124,136,143],"high":[62],"computational":[63],"cost.":[64],"This":[65],"article":[66],"presents":[67],"first":[69],"online":[70],"scheme":[73],"is":[75],"based":[76],"on":[77,96,154],"Transformers:":[79],"DQN.":[81],"In":[82],"contrast":[83],"existing":[85],"research,":[86],"our":[87,108],"novel":[88],"approach":[89,109],"demonstrate":[90],"superior":[92],"performance":[93],"with":[94],"49":[97,125,144],"games":[98,126,145],"Arcade":[101],"Learning":[102],"Environment.":[103],"The":[104,149],"results":[105],"show":[106],"achieves":[110],"significantly":[111],"higher":[112,131],"maximal":[113],"evaluation":[114,133],"scores":[115,134],"than":[116,135],"baseline":[118,137],"method":[119,138],"45":[121],"all":[123,142],"(\u223c":[127,146],"92":[128],"%),":[129],"mean":[132],"40":[140],"82":[147],"%).":[148],"code":[150],"can":[151],"be":[152],"found":[153],"https://github.com/mengli11235/SWIN-DQN.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}