{"id":"https://openalex.org/W2889665471","doi":"https://doi.org/10.1109/agents.2018.8460004","title":"Autonomous Agents in Snake Game via Deep Reinforcement Learning","display_name":"Autonomous Agents in Snake Game via Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2889665471","doi":"https://doi.org/10.1109/agents.2018.8460004","mag":"2889665471"},"language":"en","primary_location":{"id":"doi:10.1109/agents.2018.8460004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/agents.2018.8460004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Agents (ICA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dr.ntu.edu.sg/bitstream/10356/89882/1/ICA2018SnakeGame.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000166288","display_name":"Zhepei Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]},{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhepei Wei","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401420","display_name":"Di Wang","orcid":"https://orcid.org/0000-0002-3171-4001"},"institutions":[{"id":"https://openalex.org/I4210092122","display_name":"BC Research (Canada)","ror":"https://ror.org/00dr4nw61","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210092122"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":["Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly"],"affiliations":[{"raw_affiliation_string":"Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly","institution_ids":["https://openalex.org/I4210092122"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749204","display_name":"Ming Zhang","orcid":"https://orcid.org/0000-0001-6574-3006"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004167801","display_name":"Ah\u2010Hwee Tan","orcid":"https://orcid.org/0000-0003-0378-4069"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ah-Hwee Tan","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382077","display_name":"Chunyan Miao","orcid":"https://orcid.org/0000-0002-0300-3448"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chunyan Miao","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073467023","display_name":"You Zhou","orcid":"https://orcid.org/0000-0002-7081-921X"},"institutions":[{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]},{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Zhou","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000166288"],"corresponding_institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210134929"],"apc_list":null,"apc_paid":null,"fwci":1.1846,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.84532117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9882000088691711,"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":0.886093020439148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8091042637825012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6441916823387146},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5198005437850952},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4771520495414734},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4331371486186981},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09138032793998718}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.886093020439148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091042637825012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6441916823387146},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5198005437850952},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4771520495414734},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4331371486186981},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09138032793998718},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/agents.2018.8460004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/agents.2018.8460004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Agents (ICA)","raw_type":"proceedings-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/89882","is_oa":true,"landing_page_url":"http://hdl.handle.net/10220/49389","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/89882/1/ICA2018SnakeGame.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7076","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7076&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/AGENTS.2018.8460004","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/89882","is_oa":true,"landing_page_url":"http://hdl.handle.net/10220/49389","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/89882/1/ICA2018SnakeGame.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322174","display_name":"People's Government of Jilin Province","ror":"https://ror.org/02fzqav45"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2889665471.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1522301498","https://openalex.org/W1595483645","https://openalex.org/W1890963104","https://openalex.org/W2025720061","https://openalex.org/W2026461969","https://openalex.org/W2131600418","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2201581102","https://openalex.org/W2593338657","https://openalex.org/W2765830379","https://openalex.org/W2769169032","https://openalex.org/W2783268317","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6631190155","https://openalex.org/W6687681856","https://openalex.org/W6740801417"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Since":[0],"DeepMind":[1],"pioneered":[2],"a":[3,17,61,87,94,101,112,129],"deep":[4],"reinforcement":[5],"learning":[6],"(DRL)":[7],"model":[8,64,152],"to":[9,21,25,40,45,65,70,106,116,134],"play":[10,71],"the":[11,23,72,81,109,121,124,150,161],"Atari":[12],"games,":[13],"DRL":[14,63],"has":[15],"become":[16],"commonly":[18],"adopted":[19],"method":[20,133],"enable":[22,66],"agents":[24],"learn":[26],"complex":[27],"control":[28],"policies":[29],"in":[30,157],"various":[31],"video":[32],"games.":[33],"However,":[34],"similar":[35],"approaches":[36],"may":[37],"still":[38],"need":[39],"be":[41],"improved":[42],"when":[43],"applied":[44],"more":[46],"challenging":[47],"scenarios,":[48],"where":[49],"reward":[50,104],"signals":[51],"are":[52],"sparse":[53],"and":[54,127,153],"delayed.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,85,99],"develop":[60],"refined":[62],"our":[67,147],"autonomous":[68],"agent":[69,148],"classical":[73],"Snake":[74,162],"Game,":[75],"whose":[76],"constraint":[77],"gets":[78],"stricter":[79],"as":[80],"game":[82],"progresses.":[83],"Specifically,":[84],"employ":[86],"convolutional":[88],"neural":[89],"network":[90],"(CNN)":[91],"trained":[92],"with":[93],"variant":[95],"of":[96,123,159],"Q-learning.":[97],"Moreover,":[98],"propose":[100],"carefully":[102],"designed":[103],"mechanism":[105],"properly":[107],"train":[108],"network,":[110],"adopt":[111],"training":[113,119,140],"gap":[114],"strategy":[115],"temporarily":[117],"bypass":[118],"after":[120],"location":[122],"target":[125],"changes,":[126],"introduce":[128],"dual":[130],"experience":[131],"replay":[132],"categorize":[135],"different":[136],"experiences":[137],"for":[138],"better":[139],"efficacy.":[141],"The":[142],"experimental":[143],"results":[144],"show":[145],"that":[146],"outperforms":[149],"baseline":[151],"surpasses":[154],"human-level":[155],"performance":[156],"terms":[158],"playing":[160],"Game.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}