{"id":"https://openalex.org/W2890018513","doi":"https://doi.org/10.1145/3234804.3234816","title":"Survey of Deep Q-Network variants in PyGame Learning Environment","display_name":"Survey of Deep Q-Network variants in PyGame Learning Environment","publication_year":2018,"publication_date":"2018-06-27","ids":{"openalex":"https://openalex.org/W2890018513","doi":"https://doi.org/10.1145/3234804.3234816","mag":"2890018513"},"language":"en","primary_location":{"id":"doi:10.1145/3234804.3234816","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234804.3234816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Deep Learning Technologies","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/A5065806035","display_name":"\u0112valds Urt\u0101ns","orcid":"https://orcid.org/0000-0001-9813-0548"},"institutions":[{"id":"https://openalex.org/I201787326","display_name":"Riga Technical University","ror":"https://ror.org/00twb6c09","country_code":"LV","type":"education","lineage":["https://openalex.org/I201787326"]}],"countries":["LV"],"is_corresponding":true,"raw_author_name":"Evalds Urtans","raw_affiliation_strings":["Riga Technical University, Riga, Latvia"],"affiliations":[{"raw_affiliation_string":"Riga Technical University, Riga, Latvia","institution_ids":["https://openalex.org/I201787326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076897234","display_name":"Agris \u0145ikitenko","orcid":"https://orcid.org/0000-0002-5701-3094"},"institutions":[{"id":"https://openalex.org/I201787326","display_name":"Riga Technical University","ror":"https://ror.org/00twb6c09","country_code":"LV","type":"education","lineage":["https://openalex.org/I201787326"]}],"countries":["LV"],"is_corresponding":false,"raw_author_name":"Agris Nikitenko","raw_affiliation_strings":["Riga Technical University, Riga, Latvia"],"affiliations":[{"raw_affiliation_string":"Riga Technical University, Riga, Latvia","institution_ids":["https://openalex.org/I201787326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065806035"],"corresponding_institution_ids":["https://openalex.org/I201787326"],"apc_list":null,"apc_paid":null,"fwci":0.6515,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76829908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.983299970626831,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/computer-science","display_name":"Computer science","score":0.7333645820617676},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7111387252807617},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.675543487071991},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.673966646194458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6682646870613098},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6336039900779724},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5216732025146484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49761536717414856},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4684070944786072},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43992239236831665},{"id":"https://openalex.org/keywords/value-network","display_name":"Value network","score":0.4358086585998535},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12355217337608337}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333645820617676},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7111387252807617},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.675543487071991},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.673966646194458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6682646870613098},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6336039900779724},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5216732025146484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49761536717414856},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4684070944786072},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43992239236831665},{"id":"https://openalex.org/C89249532","wikidata":"https://www.wikidata.org/wiki/Q7912758","display_name":"Value network","level":3,"score":0.4358086585998535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12355217337608337},{"id":"https://openalex.org/C4216890","wikidata":"https://www.wikidata.org/wiki/Q815823","display_name":"Business model","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3234804.3234816","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234804.3234816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Deep Learning Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324128","display_name":"R\u012bgas Tehnisk\u0101 Universit\u0101te","ror":"https://ror.org/00twb6c09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2527819024","https://openalex.org/W2552220135","https://openalex.org/W2555255624","https://openalex.org/W2736601468","https://openalex.org/W2745868649","https://openalex.org/W2747402019","https://openalex.org/W2754517384","https://openalex.org/W2761873684","https://openalex.org/W2884745705","https://openalex.org/W2962858109","https://openalex.org/W2963095800","https://openalex.org/W2963184621","https://openalex.org/W2963477884","https://openalex.org/W2963641140","https://openalex.org/W2963733622","https://openalex.org/W2964043796","https://openalex.org/W3100789280","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915"],"abstract_inverted_index":{"Q-value":[0],"function":[1],"models":[2,82],"based":[3],"on":[4],"variations":[5],"of":[6,30,38,40,55,66,80],"Deep":[7,42,49,58],"Q-Network":[8,50,59],"(DQN)":[9],"have":[10],"shown":[11],"good":[12],"results":[13],"in":[14,84],"many":[15],"virtual":[16],"environments.":[17],"In":[18],"this":[19],"paper,":[20],"over":[21],"30":[22],"sub-algorithms":[23],"were":[24,46,73],"surveyed":[25],"that":[26],"influence":[27],"the":[28],"performance":[29],"DQN":[31],"variants.":[32],"Important":[33],"stability":[34],"and":[35],"repeatability":[36],"aspects":[37],"state":[39],"art":[41],"Reinforcement":[43],"Learning":[44,77],"algorithms":[45],"found.":[47],"Multi":[48],"(MDQN)":[51],"as":[52,70],"a":[53,67],"generalization":[54],"popular":[56],"Double":[57],"(DDQN)":[60],"algorithm":[61],"was":[62],"developed.":[63],"Visual":[64],"representations":[65],"learning":[68],"process":[69],"Q-Value":[71],"maps":[72],"produced":[74],"using":[75],"PyGame":[76],"Environment.":[78],"Videos":[79],"trained":[81],"available":[83],"following":[85],"link:":[86],"http://yellowrobot.xyz/mdqn":[87]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}