{"id":"https://openalex.org/W7213435339","doi":"https://doi.org/10.48550/arxiv.2609.17325","title":"Intrinsic Motivation in Reinforcement Learning: A Research Agenda for Adaptive Self-Organisation","display_name":"Intrinsic Motivation in Reinforcement Learning: A Research Agenda for Adaptive Self-Organisation","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213435339","doi":"https://doi.org/10.48550/arxiv.2609.17325"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.17325","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17325","pdf_url":"https://arxiv.org/pdf/2609.17325","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.17325","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070496798","display_name":"Anatoly Belikov","orcid":"https://orcid.org/0000-0002-9081-642X","observed_orcids":["https://orcid.org/0000-0002-9081-642X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Belikov, Anatoly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5070496798"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9994999766349792,"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":0.9994999766349792,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.0,"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-motivation","display_name":"intrinsic motivation","score":0.9760000109672546},{"id":"https://openalex.org/keywords/intrinsic-rewards","display_name":"intrinsic rewards","score":0.7910000085830688},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7490000128746033},{"id":"https://openalex.org/keywords/self-organization","display_name":"self-organization","score":0.7720000147819519},{"id":"https://openalex.org/keywords/empowerment","display_name":"empowerment","score":0.847000002861023},{"id":"https://openalex.org/keywords/curiosity","display_name":"curiosity","score":0.8730000257492065},{"id":"https://openalex.org/keywords/learning-progress","display_name":"learning progress","score":0.7509999871253967},{"id":"https://openalex.org/keywords/information-gain","display_name":"information gain","score":0.9760000109672546},{"id":"https://openalex.org/keywords/mutual-information-estimation","display_name":"mutual information estimation","score":0.9290000200271606},{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.996999979019165},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.7110000252723694},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.6299999952316284},{"id":"https://openalex.org/keywords/resource-limited-environments","display_name":"resource-constrained environments","score":0.7160000205039978},{"id":"https://openalex.org/keywords/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.7910000085830688},{"id":"https://openalex.org/keywords/motor-competence","display_name":"motor competence","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6395999789237976},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49000000953674316},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42239999771118164},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34549999237060547},{"id":"https://openalex.org/C2779918689","wikidata":"https://www.wikidata.org/wiki/Q3771842","display_name":"Stimulus (psychology)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C68784500","wikidata":"https://www.wikidata.org/wiki/Q1570691","display_name":"Adaptive behavior","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C164380108","wikidata":"https://www.wikidata.org/wiki/Q507187","display_name":"Attractor","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C92393732","wikidata":"https://www.wikidata.org/wiki/Q1790374","display_name":"Learning theory","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2910496060","wikidata":"https://www.wikidata.org/wiki/Q4680720","display_name":"Adaptive behaviour","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.17325","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17325","pdf_url":"https://arxiv.org/pdf/2609.17325","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.17325","doi":"https://doi.org/10.48550/arxiv.2609.17325","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.17325","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.17325","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17325","pdf_url":"https://arxiv.org/pdf/2609.17325","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213435339.pdf","grobid_xml":"https://content.openalex.org/works/W7213435339.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1591713425","https://openalex.org/W1959608418","https://openalex.org/W2034806191","https://openalex.org/W2098010659","https://openalex.org/W2119007372","https://openalex.org/W2130497602","https://openalex.org/W2465725878","https://openalex.org/W2467604901","https://openalex.org/W2589249864","https://openalex.org/W2788741142","https://openalex.org/W3037248211","https://openalex.org/W3092398301","https://openalex.org/W4297808394","https://openalex.org/W4306774308","https://openalex.org/W4307901249","https://openalex.org/W4313244913","https://openalex.org/W4399223951","https://openalex.org/W4409147637","https://openalex.org/W4410942610","https://openalex.org/W4415963673","https://openalex.org/W4416113521"],"related_works":["https://openalex.org/W7095809709","https://openalex.org/W2109420588","https://openalex.org/W3193962195","https://openalex.org/W2164424353","https://openalex.org/W2129233289","https://openalex.org/W4407822334","https://openalex.org/W2949969799","https://openalex.org/W3111378514","https://openalex.org/W7048160779","https://openalex.org/W355724390"],"abstract_inverted_index":{"Biological":[0],"cells":[1,24],"can":[2,46,152,192],"be":[3],"viewed":[4],"as":[5],"individual,":[6],"interacting":[7],"agents":[8,164],"whose":[9],"collective":[10],"dynamics":[11],"give":[12],"rise":[13],"to":[14,27,87,147,187,194],"adaptive":[15,195],"behaviour":[16],"at":[17,116,197],"multiple":[18,117],"levels":[19],"of":[20,76,157,162],"organisation,":[21],"from":[22],"individual":[23],"through":[25],"tissues":[26],"whole":[28],"multicellular":[29],"organisms.":[30],"In":[31],"this":[32,125],"perspective":[33],"and":[34,51,73,120,169],"tutorial":[35],"article":[36],"we":[37,127],"discuss":[38],"whether":[39,149,189],"intrinsic":[40,80,158,167,190],"rewards":[41],"in":[42,137,174],"artificial":[43],"neural":[44],"systems":[45,108],"support":[47],"adaptation,":[48],"functional":[49],"specialisation":[50],"higher-level":[52],"self-organisation":[53],"without":[54],"a":[55,134,170],"shared":[56],"external":[57],"objective.":[58],"We":[59,103],"review":[60],"empowerment,":[61],"curiosity,":[62],"learning":[63,115,191],"progress,":[64],"information":[65,71],"gain,":[66],"unsupervised":[67],"skill":[68],"discovery,":[69],"mutual":[70],"estimation":[72],"the":[74],"use":[75],"world":[77],"models":[78],"for":[79],"reward":[81],"computation.":[82],"Particular":[83],"attention":[84],"is":[85],"given":[86],"failure":[88,155],"modes":[89,156],"showing":[90],"when":[91],"such":[92],"objectives":[93],"do":[94],"not":[95],"produce":[96],"sustained":[97],"exploration":[98],"or":[99],"increasingly":[100],"complex":[101],"behaviour.":[102,182],"argue":[104],"that":[105],"more":[106],"capable":[107],"may":[109],"require":[110],"complementary":[111],"objectives,":[112],"communication,":[113],"memory,":[114],"temporal":[118],"scales":[119],"environmental":[121,150],"constraints.":[122],"Based":[123],"on":[124],"perspective,":[126],"outline":[128],"three":[129],"experimental":[130],"directions.":[131],"These":[132,183],"include":[133],"resource-constrained":[135],"environment":[136],"which":[138,175],"otherwise":[139],"stable":[140],"behavioural":[141],"attractors":[142],"become":[143],"unsustainable,":[144],"allowing":[145],"us":[146],"test":[148,188],"constraints":[151],"mitigate":[153],"characteristic":[154],"objectives.":[159],"The":[160],"network":[161],"recurrent":[163],"with":[165],"per-agent":[166],"rewards,":[168],"hierarchical":[171],"world-model":[172],"agent":[173],"exploratory":[176],"motor":[177],"competence":[178],"develops":[179],"before":[180],"goal-directed":[181],"experiments":[184],"are":[185],"intended":[186],"lead":[193],"organisation":[196],"progressively":[198],"higher":[199],"levels.":[200]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-17T00:00:00"}