If you are acting on the environment to obtain information, you are "supervised" by the environment and your action involves decision theory parameterized by a value function in an explore/exploit tradeoff. This corresponds to engineering/technology and it is what living things do.
If your learning does not involve acquisition of information, then your value function is to minimize the size of the program that outputs the information you have, which has been proven to produce the model that optimally predicts missing data (whether present or prospective) in the sense that the model's predictions are more likely to be correct than any other model. This is "unsupervised", and corresponds to "value free science". ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T77af318d4abfa8a8-Ma5f01c87a1095771f708596e Delivery options: https://agi.topicbox.com/groups/agi/subscription
