{"id":101142,"date":"2020-01-21T09:03:17","date_gmt":"2020-01-21T17:03:17","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2020\/01\/the-brain-predicts-reward-like-an-ai-says-new-deepmind-research"},"modified":"2020-01-21T09:03:17","modified_gmt":"2020-01-21T17:03:17","slug":"the-brain-predicts-reward-like-an-ai-says-new-deepmind-research","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2020\/01\/the-brain-predicts-reward-like-an-ai-says-new-deepmind-research","title":{"rendered":"The Brain Predicts Reward Like an AI, Says New DeepMind Research"},"content":{"rendered":"<p style=\"padding-right: 20px\"><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/the-brain-predicts-reward-like-an-ai-says-new-deepmind-research3.jpg\"><\/a><\/p>\n<p>We all subconsciously learn complex behaviors in response to positive and negative feedback, but how that works in the brain remains a century-long mystery. By examining a powerful variant of reinforcement learning, dubbed distributional reinforcement learning, that outperforms original methods, the team suggests that the brain may simultaneously represent multiple <i>predicted<\/i> futures in parallel. Each future is assigned a different probability, or <i>chance<\/i> of actually occurring, based on reward.<\/p>\n<p>Here\u2019s the kicker: the team didn\u2019t leave it as an AI-inspired hypothesis. In a collaboration with a lab at Harvard University, they recording straight from a mouse\u2019s brain, and found signs of their idea encoded in its reward-processing neurons.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We all subconsciously learn complex behaviors in response to positive and negative feedback, but how that works in the brain remains a century-long mystery. By examining a powerful variant of reinforcement learning, dubbed distributional reinforcement learning, that outperforms original methods, the team suggests that the brain may simultaneously represent multiple predicted futures in parallel. Each [\u2026]<\/p>\n","protected":false},"author":534,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20,6],"tags":[],"class_list":["post-101142","post","type-post","status-publish","format-standard","hentry","category-futurism","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/101142","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/534"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=101142"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/101142\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=101142"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=101142"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=101142"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}