Differences

This shows you the differences between two versions of the page.

--- public:t-720-atai:atai-22:agents_and_control [2022/09/17 09:57] – [Inferred GMI Architectural Features] thorisson
+++ public:t-720-atai:atai-22:agents_and_control [2024/04/29 13:33] (current) – external edit 127.0.0.1
@@ Line 279: / Line 279: @@
 ====Learning RPR Controllers Must Also Classify====
-|  Classification  | To act, one needs to know what to act on. \\ To know what to act on, one needs to classify. \\ To classify, one needs to sense. \\ To sense, one needs measurement devices.    |
+|  \\ Classification  | To act, one needs to know what to act on. \\ To know what to act on, one needs to classify. \\ To classify, one needs to sense. \\ To sense, one needs measurement devices.    |
 |  Learning to Classify  | In a world with a lot of variation, a learning controller must also learn to classify. \\ To learn to classify, one must learn what to control to classify appropriately. \\ Learning to control, therefore, requires learning two kinds of classification  (at the very least).   |
 |  ANNs  | Contemporary ANNs (e.g. Deep Neural Networks, Double-Deep Q-Learners, etc.) can only do classification. They can only do classification by going through a long continuous training session, after which the learning is turned off.   |