{"id":"https://openalex.org/W3182544545","doi":"https://doi.org/10.1109/cog52621.2021.9618997","title":"Distilling Reinforcement Learning Tricks for Video Games","display_name":"Distilling Reinforcement Learning Tricks for Video Games","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3182544545","doi":"https://doi.org/10.1109/cog52621.2021.9618997","mag":"3182544545"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9618997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9618997","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.00703","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048689678","display_name":"Anssi Kanervisto","orcid":"https://orcid.org/0000-0002-7479-4574"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Anssi Kanervisto","raw_affiliation_strings":["School of Computing University of Eastern Finland, Joensuu, Finland","University of Eastern Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009506955","display_name":"Christian Scheller","orcid":"https://orcid.org/0000-0002-9624-1487"},"institutions":[{"id":"https://openalex.org/I2972652528","display_name":"FHNW University of Applied Sciences and Arts","ror":"https://ror.org/04mq2g308","country_code":"CH","type":"education","lineage":["https://openalex.org/I2972652528"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christian Scheller","raw_affiliation_strings":["Institute for Data Science University of Applied Sciences Northwestern Switzerland, Windisch, Switzerland"],"affiliations":[{"raw_affiliation_string":"Institute for Data Science University of Applied Sciences Northwestern Switzerland, Windisch, Switzerland","institution_ids":["https://openalex.org/I2972652528"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009427213","display_name":"Yanick Schraner","orcid":null},"institutions":[{"id":"https://openalex.org/I2972652528","display_name":"FHNW University of Applied Sciences and Arts","ror":"https://ror.org/04mq2g308","country_code":"CH","type":"education","lineage":["https://openalex.org/I2972652528"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yanick Schraner","raw_affiliation_strings":["Institute for Data Science University of Applied Sciences Northwestern Switzerland, Windisch, Switzerland"],"affiliations":[{"raw_affiliation_string":"Institute for Data Science University of Applied Sciences Northwestern Switzerland, Windisch, Switzerland","institution_ids":["https://openalex.org/I2972652528"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Hautamaki","raw_affiliation_strings":["School of Computing University of Eastern Finland, Joensuu, Finland","University of Eastern Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048689678"],"corresponding_institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"],"apc_list":null,"apc_paid":null,"fwci":0.12261971,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.33121495,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"04"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9962999820709229,"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":0.9884999990463257,"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":0.9159834384918213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7986451387405396},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6607083082199097},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5967604517936707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5185340046882629},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5016763210296631},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3781343102455139},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08949622511863708},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08882862329483032},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06802874803543091}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9159834384918213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986451387405396},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6607083082199097},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5967604517936707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185340046882629},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5016763210296631},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3781343102455139},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08949622511863708},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08882862329483032},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06802874803543091},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cog52621.2021.9618997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9618997","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"},{"id":"pmh:oai:arXiv.org:2107.00703","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.00703","pdf_url":"https://arxiv.org/pdf/2107.00703","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:3182544545","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2107.00703","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2107.00703","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.00703","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.00703","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.00703","pdf_url":"https://arxiv.org/pdf/2107.00703","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3182544545.pdf","grobid_xml":"https://content.openalex.org/works/W3182544545.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2145339207","https://openalex.org/W2296073425","https://openalex.org/W2522489477","https://openalex.org/W2553701371","https://openalex.org/W2751516180","https://openalex.org/W2810602713","https://openalex.org/W2941355526","https://openalex.org/W2962747693","https://openalex.org/W2963871073","https://openalex.org/W2963948533","https://openalex.org/W2965908679","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2997502221","https://openalex.org/W3035868808","https://openalex.org/W3089895152","https://openalex.org/W3094236223","https://openalex.org/W3094597259","https://openalex.org/W3203637370","https://openalex.org/W6638088447","https://openalex.org/W6729788943","https://openalex.org/W6743660412","https://openalex.org/W6774279402","https://openalex.org/W6775892990","https://openalex.org/W6780032859","https://openalex.org/W6784190213","https://openalex.org/W6784215824"],"related_works":["https://openalex.org/W3024023292","https://openalex.org/W3047210685","https://openalex.org/W3202184901","https://openalex.org/W3199500857","https://openalex.org/W3212146301","https://openalex.org/W3110775170","https://openalex.org/W3012544020","https://openalex.org/W3049240648","https://openalex.org/W3014728935","https://openalex.org/W2899054334","https://openalex.org/W3041878969","https://openalex.org/W2415726935","https://openalex.org/W2808007596","https://openalex.org/W2996320348","https://openalex.org/W113028485","https://openalex.org/W2737857002","https://openalex.org/W2935062270","https://openalex.org/W3014664339","https://openalex.org/W3040707741","https://openalex.org/W2897432694"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"research":[3],"focuses":[4],"on":[5],"general":[6],"solutions":[7],"that":[8,19],"can":[9,22,93],"be":[10,39],"applied":[11],"across":[12],"different":[13],"domains.":[14,127],"This":[15],"results":[16,69,86],"in":[17,24,125],"methods":[18,112],"RL":[20,72,111],"practitioners":[21],"use":[23,43],"almost":[25],"any":[26],"domain.":[27],"However,":[28],"recent":[29],"studies":[30],"often":[31],"lack":[32],"the":[33,76],"engineering":[34,77],"steps":[35],"(\"tricks\")":[36],"which":[37],"may":[38],"needed":[40],"to":[41,66,107],"effectively":[42],"RL,":[44],"such":[45],"as":[46],"reward":[47],"shaping,":[48],"curriculum":[49],"learning,":[50],"and":[51,70,87,122],"splitting":[52],"a":[53,95,118],"large":[54],"task":[55],"into":[56],"smaller":[57],"chunks.":[58],"Such":[59],"tricks":[60,83,92,115],"are":[61],"common,":[62],"if":[63],"not":[64],"necessary,":[65],"achieve":[67],"state-of-the-art":[68,85],"win":[71],"competitions.":[73],"To":[74],"ease":[75],"efforts,":[78],"we":[79],"distill":[80],"descriptions":[81],"of":[82,103],"from":[84],"study":[88],"how":[89],"well":[90],"these":[91],"improve":[94],"standard":[96],"deep":[97],"Q-learning":[98],"agent.":[99],"The":[100],"long-term":[101],"goal":[102],"this":[104],"work":[105],"is":[106],"enable":[108],"combining":[109],"proven":[110],"with":[113],"domain-specific":[114],"by":[116],"providing":[117],"unified":[119],"software":[120],"framework":[121],"accompanying":[123],"insights":[124],"multiple":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}