{"id":"https://openalex.org/W2663108269","doi":"https://doi.org/10.24963/ijcai.2017/344","title":"Count-Based Exploration in Feature Space for Reinforcement Learning","display_name":"Count-Based Exploration in Feature Space for Reinforcement Learning","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2663108269","doi":"https://doi.org/10.24963/ijcai.2017/344","mag":"2663108269"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/344","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/344","pdf_url":"https://www.ijcai.org/proceedings/2017/0344.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0344.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062765886","display_name":"Jarryd Martin","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jarryd Martin","raw_affiliation_strings":["Australian National University","Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084446448","display_name":"Suraj Narayanan Sasikumar","orcid":"https://orcid.org/0000-0003-3321-4411"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Suraj Narayanan S.","raw_affiliation_strings":["Australian National University"],"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020224050","display_name":"Tom Everitt","orcid":"https://orcid.org/0000-0003-1210-9866"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tom Everitt","raw_affiliation_strings":["Australian National University","Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073944062","display_name":"Marcus H\u00fctter","orcid":"https://orcid.org/0000-0002-3263-4097"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Marcus Hutter","raw_affiliation_strings":["Australian National University","Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062765886"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":4.3566,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95440138,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2471","last_page":"2478"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9918000102043152,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9911999702453613,"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":0.898303747177124},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6602110862731934},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6330576539039612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6215242743492126},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6168515086174011},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5976876616477966},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.56960529088974},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5624351501464844},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5514482259750366},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5219342708587646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5193485021591187},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5187625885009766},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42550987005233765},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3829028308391571},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3213069438934326},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3096944987773895},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.281948447227478},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16270071268081665}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.898303747177124},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6602110862731934},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6330576539039612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6215242743492126},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6168515086174011},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5976876616477966},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.56960529088974},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5624351501464844},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5514482259750366},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5219342708587646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5193485021591187},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5187625885009766},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42550987005233765},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3829028308391571},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3213069438934326},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3096944987773895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.281948447227478},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16270071268081665},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2017/344","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/344","pdf_url":"https://www.ijcai.org/proceedings/2017/0344.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1706.08090","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.08090","pdf_url":"https://arxiv.org/pdf/1706.08090","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":"text"},{"id":"mag:2663108269","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1706.08090","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.1706.08090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1706.08090","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":"doi:10.24963/ijcai.2017/344","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/344","pdf_url":"https://www.ijcai.org/proceedings/2017/0344.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2663108269.pdf","grobid_xml":"https://content.openalex.org/works/W2663108269.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W779494576","https://openalex.org/W1491843047","https://openalex.org/W1988526405","https://openalex.org/W2077052576","https://openalex.org/W2121863487","https://openalex.org/W2123447947","https://openalex.org/W2124352385","https://openalex.org/W2124403132","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2190606234","https://openalex.org/W2280163991","https://openalex.org/W2419612459","https://openalex.org/W2509374375","https://openalex.org/W2949475445","https://openalex.org/W2949608212","https://openalex.org/W2962767126","https://openalex.org/W2964043796","https://openalex.org/W3103780890"],"related_works":["https://openalex.org/W2963359646","https://openalex.org/W2145339207","https://openalex.org/W1988526405","https://openalex.org/W2561776174","https://openalex.org/W2764311431","https://openalex.org/W3103780890","https://openalex.org/W2419612459","https://openalex.org/W2139612737","https://openalex.org/W2121863487","https://openalex.org/W2614839826","https://openalex.org/W2596982695","https://openalex.org/W2034806191","https://openalex.org/W779494576","https://openalex.org/W2964043796","https://openalex.org/W2899205164","https://openalex.org/W2417786368","https://openalex.org/W2257979135","https://openalex.org/W2173248099","https://openalex.org/W3211416934","https://openalex.org/W2605070055"],"abstract_inverted_index":{"We":[0,84],"introduce":[1],"a":[2,86,91],"new":[3,87],"count-based":[4],"optimistic":[5],"exploration":[6,74],"algorithm":[7,140],"for":[8,89,123,144],"Reinforcement":[9],"Learning":[10],"(RL)":[11],"that":[12,76,120,128],"is":[13,121,158],"feasible":[14],"in":[15,26,45,146,151],"environments":[16],"with":[17,72,104],"high-dimensional":[18,174],"state-action":[19],"spaces.":[20],"The":[21,138,156],"success":[22],"of":[23,51,68,116],"RL":[24,41,70,175],"algorithms":[25,71],"these":[27],"domains":[28],"depends":[29],"crucially":[30],"on":[31,173],"generalisation":[32,60,110],"from":[33],"limited":[34],"training":[35],"experience.":[36],"Function":[37],"approximation":[38],"techniques":[39],"enable":[40,59],"agents":[42],"to":[43,47,80,99],"generalise":[44],"order":[46],"estimate":[48,100],"the":[49,66,78,97,101,117,142,152],"value":[50,124],"unvisited":[52],"states,":[53],"but":[54],"at":[55],"present":[56,85],"few":[57],"methods":[58],"regarding":[61],"uncertainty.":[62,83],"This":[63],"has":[64],"prevented":[65],"combination":[67],"scalable":[69],"efficient":[73],"strategies":[75],"drive":[77],"agent":[79,98,143],"reduce":[81],"its":[82],"method":[88,157],"computing":[90],"generalised":[92],"state":[93,118,154],"visit-count,":[94],"which":[95],"allows":[96],"uncertainty":[102],"associated":[103],"any":[105],"state.":[106],"Our":[107],"\\phi-pseudocount":[108],"achieves":[109,169],"by":[111],"exploiting":[112],"same":[113],"feature":[114,147],"representation":[115],"space":[119,148],"used":[122],"function":[125],"approximation.":[126],"States":[127],"have":[129],"less":[130,161],"frequently":[131],"observed":[132],"features":[133],"are":[134],"deemed":[135],"more":[136],"uncertain.":[137],"\\phi-Exploration-Bonus":[139],"rewards":[141],"exploring":[145],"rather":[149],"than":[150,164],"untransformed":[153],"space.":[155],"simpler":[159],"and":[160,168],"computationally":[162],"expensive":[163],"some":[165],"previous":[166],"proposals,":[167],"near":[170],"state-of-the-art":[171],"results":[172],"benchmarks.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}