{"id":414,"date":"2026-01-06T00:49:46","date_gmt":"2026-01-06T00:49:46","guid":{"rendered":"https:\/\/braininspiredrobotics.com\/?p=414"},"modified":"2026-01-06T00:49:46","modified_gmt":"2026-01-06T00:49:46","slug":"what-neuroscience-can-tell-ai-about-learning-in-continuously-changing-environments","status":"publish","type":"post","link":"https:\/\/braininspiredrobotics.com\/?p=414","title":{"rendered":"What neuroscience can tell AI about learning in continuously changing environments?"},"content":{"rendered":"<p style=\"text-align: justify;\">Durstewitz, D., Averbeck, B. &amp; Koppe, G. <a href=\"https:\/\/www.nature.com\/articles\/s42256-025-01146-z\"><strong>What neuroscience can tell AI about learning in continuously changing environments<\/strong><\/a>. Nature Machine Intelligence 7, 1897\u20131912 (2025). https:\/\/doi.org\/10.1038\/s42256-025-01146-z<\/p>\n<p style=\"text-align: justify;\">Abstract<br \/>\n&#8220;Modern artificial intelligence (AI) models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task and then deployed with fixed parameters. Their training is costly, slow and gradual, requiring billions of repetitions. In stark contrast, <strong><span style=\"color: #ff0000;\">animals continuously adapt to the ever-changing contingencies in their environments<\/span><\/strong>. This is particularly important for social species, where behavioural policies and reward outcomes may frequently change in interaction with peers. The underlying computational processes are often marked by rapid shifts in an animal\u2019s behaviour and rather sudden transitions in neuronal population activity. Such computational capacities are of growing importance for AI systems operating in the real world, like those guiding robots or autonomous vehicles, or for agentic AI interacting with humans online. <strong><span style=\"color: #ff0000;\">Can AI learn from neuroscience?<\/span> <\/strong>This Perspective explores this question, <strong><span style=\"color: #ff0000;\">integrating the literature on continual and in-context learning in AI with the neuroscience of learning on behavioural tasks with shifting rules, reward probabilities or outcomes<\/span><\/strong>. We outline an agenda for <strong><span style=\"color: #ff0000;\">how the links between neuroscience and AI could be tightened, thus supporting the transfer of ideas and findings between both areas and contributing to the evolving field of NeuroAI<\/span><\/strong>.&#8221;<\/p>\n<p style=\"text-align: justify;\">Durstewitz, D., Averbeck, B. &amp; Koppe, G. <a href=\"https:\/\/www.nature.com\/articles\/s42256-025-01146-z\"><strong>What neuroscience can tell AI about learning in continuously changing environments<\/strong><\/a>. Nature Machine Intelligence 7, 1897\u20131912 (2025). https:\/\/doi.org\/10.1038\/s42256-025-01146-z<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Durstewitz, D., Averbeck, B. &amp; Koppe, G. What neuroscience can tell AI about learning in continuously changing environments. Nature Machine Intelligence 7, 1897\u20131912 (2025). https:\/\/doi.org\/10.1038\/s42256-025-01146-z Abstract &#8220;Modern artificial intelligence (AI) models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task and then deployed [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[107,6],"tags":[134,135,133],"class_list":["post-414","post","type-post","status-publish","format-standard","hentry","category-natural-intelligence","category-neuromorphic-intelligence","tag-continual-learning","tag-in-context-learning","tag-neuroai"],"_links":{"self":[{"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/posts\/414","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=414"}],"version-history":[{"count":1,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/posts\/414\/revisions"}],"predecessor-version":[{"id":415,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/posts\/414\/revisions\/415"}],"wp:attachment":[{"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=414"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=414"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=414"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}