{"id":"https://openalex.org/W2949969799","doi":"https://doi.org/10.48550/arxiv.1906.07865","title":"Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study","display_name":"Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study","publication_year":2019,"publication_date":"2019-06-19","ids":{"openalex":"https://openalex.org/W2949969799","doi":"https://doi.org/10.48550/arxiv.1906.07865","mag":"2949969799"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1906.07865","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07865","pdf_url":"https://arxiv.org/pdf/1906.07865","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.07865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034405341","display_name":"Cameron Linke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Linke, Cam","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017182587","display_name":"Nadia M. Ady","orcid":"https://orcid.org/0009-0003-3314-3008","observed_orcids":["https://orcid.org/0009-0003-3314-3008"]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ady, Nadia M.","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101613484","display_name":"Martha White","orcid":"https://orcid.org/0000-0002-5356-2950","observed_orcids":["https://orcid.org/0000-0002-5356-2950"]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"White, Martha","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026582515","display_name":"Thomas Degris","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Degris, Thomas","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101954122","display_name":"Adam White","orcid":"https://orcid.org/0000-0002-6449-0622","observed_orcids":["https://orcid.org/0000-0002-6449-0622"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"White, Adam","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0013000000035390258,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.00019999999494757503,"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/intrinsic-rewards","display_name":"intrinsic rewards","score":0.9819999933242798},{"id":"https://openalex.org/keywords/parallel-learning","display_name":"parallel learning","score":0.5490000247955322},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.5460000038146973},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.8389999866485596},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.6690000295639038},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.6290000081062317}],"concepts":[{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.6459630727767944},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5163049101829529},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.430090069770813},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.30577749013900757},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19973206520080566},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1854037344455719}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1906.07865","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07865","pdf_url":"https://arxiv.org/pdf/1906.07865","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1906.07865","doi":"https://doi.org/10.48550/arxiv.1906.07865","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.07865","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.07865","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07865","pdf_url":"https://arxiv.org/pdf/1906.07865","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W157259654","https://openalex.org/W172143579","https://openalex.org/W175273776","https://openalex.org/W248046807","https://openalex.org/W326419249","https://openalex.org/W567721252","https://openalex.org/W779494576","https://openalex.org/W839588591","https://openalex.org/W1505937442","https://openalex.org/W1515933446","https://openalex.org/W1546066630","https://openalex.org/W1754268392","https://openalex.org/W1863227302","https://openalex.org/W1917036087","https://openalex.org/W2020920737","https://openalex.org/W2022163520","https://openalex.org/W2034284198","https://openalex.org/W2034960258","https://openalex.org/W2056707879","https://openalex.org/W2078150668","https://openalex.org/W2085754318","https://openalex.org/W2096765209","https://openalex.org/W2101524054","https://openalex.org/W2109910161","https://openalex.org/W2120889539","https://openalex.org/W2121863487","https://openalex.org/W2132622533","https://openalex.org/W2135664069","https://openalex.org/W2139612737","https://openalex.org/W2144744117","https://openalex.org/W2149660380","https://openalex.org/W2158596240","https://openalex.org/W2160589914","https://openalex.org/W2163533082","https://openalex.org/W2168339290","https://openalex.org/W2177172828","https://openalex.org/W2188721763","https://openalex.org/W2299529128","https://openalex.org/W2301341004","https://openalex.org/W2335959470","https://openalex.org/W2417786368","https://openalex.org/W2419612459","https://openalex.org/W2549443287","https://openalex.org/W2551887912","https://openalex.org/W2561776174","https://openalex.org/W2591037921","https://openalex.org/W2593766708","https://openalex.org/W2663108269","https://openalex.org/W2731828881","https://openalex.org/W2733961795","https://openalex.org/W2739068567","https://openalex.org/W2745820874","https://openalex.org/W2751973545","https://openalex.org/W2765298920","https://openalex.org/W2785542505","https://openalex.org/W2786917922","https://openalex.org/W2788781499","https://openalex.org/W2796618762","https://openalex.org/W2898155524","https://openalex.org/W2903158431","https://openalex.org/W2921837734","https://openalex.org/W2946704039","https://openalex.org/W2948199691","https://openalex.org/W2949071206","https://openalex.org/W2951571771","https://openalex.org/W2962795549","https://openalex.org/W2963331157","https://openalex.org/W2963604043","https://openalex.org/W2963712109","https://openalex.org/W2963979925","https://openalex.org/W2964083594","https://openalex.org/W2964121744","https://openalex.org/W2964327384","https://openalex.org/W2995912970","https://openalex.org/W3017190086","https://openalex.org/W3037660226","https://openalex.org/W3041929019","https://openalex.org/W3111378514"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W2931662336","https://openalex.org/W2504683458","https://openalex.org/W2260035126","https://openalex.org/W2077865380","https://openalex.org/W2765597752","https://openalex.org/W2134894512","https://openalex.org/W2083375246","https://openalex.org/W2010073985"],"abstract_inverted_index":{"Learning":[0],"about":[1],"many":[2,16,115],"things":[3],"can":[4,223],"provide":[5,188],"numerous":[6],"benefits":[7],"to":[8,22,28,44,50,69,86],"a":[9,60,124,148,189,209],"reinforcement":[10,84,201],"learning":[11,15,53,58,85,119,126,176,202,222],"system.":[12],"For":[13],"example,":[14],"auxiliary":[17,80],"value":[18,63],"functions,":[19],"in":[20,39,123,147],"addition":[21],"optimizing":[23],"the":[24,46,52,57,76,103,114,155,164,219],"environmental":[25,129],"reward,":[26],"appears":[27],"improve":[29],"both":[30],"exploration":[31],"and":[32,82,99,141,159,162,181,203],"representation":[33],"learning.":[34,205],"The":[35],"question":[36],"we":[37,139],"tackle":[38],"this":[40,93,137],"paper":[41],"is":[42,68,131,179,185,231],"how":[43],"sculpt":[45],"stream":[47],"of":[48,59,62,78,105,107,113,118,166,175,193,221],"experience---how":[49],"adapt":[51],"system's":[54],"behavior---to":[55],"optimize":[56],"collection":[61],"functions.":[64],"A":[65],"simple":[66,94,210],"answer":[67],"compute":[70],"an":[71],"intrinsic":[72,89,144,215],"reward":[73,130,145,158],"based":[74,217],"on":[75,218],"statistics":[77],"each":[79,228],"learner,":[81],"use":[83],"maximize":[87],"that":[88,171],"reward.":[90],"Unfortunately,":[91],"implementing":[92],"idea":[95],"has":[96,101],"proven":[97],"difficult,":[98],"thus":[100],"been":[102],"focus":[104],"decades":[106],"study.":[108],"It":[109],"remains":[110],"unclear":[111],"which":[112],"possible":[116],"measures":[117],"would":[120],"work":[121],"well":[122],"parallel":[125],"setting":[127],"where":[128],"extremely":[132],"sparse":[133],"or":[134],"absent.":[135],"In":[136],"paper,":[138],"investigate":[140],"compare":[142],"different":[143,195],"mechanisms":[146],"new":[149],"bandit-like":[150],"parallel-learning":[151],"testbed.":[152],"We":[153,187],"discuss":[154],"interaction":[156],"between":[157],"prediction":[160,168],"learners":[161],"highlight":[163,208],"importance":[165],"introspective":[167],"learners:":[169],"those":[170],"increase":[172],"their":[173],"rate":[174],"when":[177,183],"progress":[178],"possible,":[180],"decrease":[182],"it":[184],"not.":[186],"comprehensive":[190],"empirical":[191],"comparison":[192],"14":[194],"rewards,":[196],"including":[197],"well-known":[198],"ideas":[199],"from":[200],"active":[204],"Our":[206],"results":[207],"but":[211],"seemingly":[212],"powerful":[213],"principle:":[214],"rewards":[216],"amount":[220],"generate":[224],"useful":[225],"behavior,":[226],"if":[227],"individual":[229],"learner":[230],"introspective.":[232]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}