{"id":"https://openalex.org/W3041692865","doi":"https://doi.org/10.24963/ijcai.2020/651","title":"Playing Atari with Six Neurons (Extended Abstract)","display_name":"Playing Atari with Six Neurons (Extended Abstract)","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3041692865","doi":"https://doi.org/10.24963/ijcai.2020/651","mag":"3041692865"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/651","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/651","pdf_url":"https://www.ijcai.org/proceedings/2020/0651.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0651.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009996780","display_name":"Giuseppe Cuccu","orcid":"https://orcid.org/0000-0002-1005-5246"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Giuseppe Cuccu","raw_affiliation_strings":["eXascale Infolab, Department of Computer Science, University of Fribourg, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"eXascale Infolab, Department of Computer Science, University of Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077267552","display_name":"Julian Togelius","orcid":"https://orcid.org/0000-0003-3128-4598"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Togelius","raw_affiliation_strings":["Game Innovation Lab, Tandon School of Engineering, New York University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Game Innovation Lab, Tandon School of Engineering, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028454093","display_name":"Philippe Cudr\u00e9-Mauroux","orcid":"https://orcid.org/0000-0003-2588-4212"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philippe Cudr\u00e9-Mauroux","raw_affiliation_strings":["eXascale Infolab, Department of Computer Science, University of Fribourg, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"eXascale Infolab, Department of Computer Science, University of Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4711","last_page":"4715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.994700014591217,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8223907947540283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7742916941642761},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6791086196899414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6450345516204834},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5374088883399963},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.530457615852356},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48383012413978577},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4786428213119507},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4749988317489624},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.4698407053947449},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4638967514038086},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38538190722465515},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3217236399650574},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3111559748649597},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12475168704986572}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8223907947540283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742916941642761},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6791086196899414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6450345516204834},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5374088883399963},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.530457615852356},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48383012413978577},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4786428213119507},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4749988317489624},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.4698407053947449},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4638967514038086},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38538190722465515},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3217236399650574},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3111559748649597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12475168704986572},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/651","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/651","pdf_url":"https://www.ijcai.org/proceedings/2020/0651.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/651","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/651","pdf_url":"https://www.ijcai.org/proceedings/2020/0651.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3041692865.pdf","grobid_xml":"https://content.openalex.org/works/W3041692865.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1547737196","https://openalex.org/W1674110665","https://openalex.org/W2099397840","https://openalex.org/W2111935653","https://openalex.org/W2124290836","https://openalex.org/W2136495462","https://openalex.org/W2145339207","https://openalex.org/W2171658832","https://openalex.org/W2596367596","https://openalex.org/W2761873684","https://openalex.org/W2778749116","https://openalex.org/W2779977383","https://openalex.org/W2792919371","https://openalex.org/W2807228161","https://openalex.org/W2962699241","https://openalex.org/W2962991582","https://openalex.org/W2963790038","https://openalex.org/W3103780890"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,90],"learning":[2,77],"applied":[3],"to":[4,13,62,119,153],"vision-based":[5],"problems":[6],"like":[7],"Atari":[8,144],"games":[9,145],"maps":[10],"pixels":[11],"directly":[12],"actions;":[14],"internally,":[15],"the":[16,21,44,109,158],"deep":[17],"neural":[18,148],"network":[19],"bears":[20],"responsibility":[22],"of":[23,46,112,143,150,165,177],"both":[24],"extracting":[25],"useful":[26],"information":[27,134],"and":[28,64,79,123],"making":[29],"decisions":[30],"based":[31,99],"on":[32,100,140,157],"it.":[33],"By":[34],"separating":[35],"image":[36],"processing":[37],"from":[38],"decision-making,":[39],"one":[40],"could":[41],"better":[42],"understand":[43,63],"complexity":[45],"each":[47],"task,":[48],"as":[49,51],"well":[50],"potentially":[52],"find":[53],"smaller":[54],"policy":[55,87],"representations":[56,82,93],"that":[57],"are":[58,94,162],"easier":[59],"for":[60,76,86,132],"humans":[61],"may":[65],"generalize":[66],"better.":[67],"To":[68],"this":[69],"end,":[70],"we":[71],"propose":[72],"a":[73,141],"new":[74,121],"method":[75],"policies":[78],"compact":[80],"state":[81],"separately":[83],"but":[84],"simultaneously":[85],"approximation":[88],"in":[89],"learning.":[91],"State":[92],"generated":[95],"by":[96,130],"an":[97],"encoder":[98,110],"two":[101,175],"novel":[102],"algorithms:":[103],"Increasing":[104],"Dictionary":[105],"Vector":[106],"Quantization":[107],"makes":[108],"capable":[111,164],"growing":[113],"its":[114],"dictionary":[115],"size":[116],"over":[117],"time,":[118],"address":[120],"observations;":[122],"Direct":[124],"Residuals":[125],"Sparse":[126],"Coding":[127],"encodes":[128],"observations":[129],"aiming":[131],"highest":[133],"inclusion.":[135],"We":[136],"test":[137],"our":[138],"system":[139],"selection":[142],"using":[146],"tiny":[147],"networks":[149],"only":[151],"6":[152],"18":[154],"neurons":[155],"(depending":[156],"game's":[159],"controls).":[160],"These":[161],"still":[163],"achieving":[166],"results":[167],"comparable---and":[168],"occasionally":[169],"superior---to":[170],"state-of-the-art":[171],"techniques":[172],"which":[173],"use":[174],"orders":[176],"magnitude":[178],"more":[179],"neurons.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}