Epstein Secrets

to learn procedures that will maxi- mize some Goal whose Truth Value is estimated via an expected reward calculation (where "reward" may mean simply the Truth Value of some Atom defined as "reward"). Goal-driven learning is more general than reinforcement learning as thus defined; and the learning that CogPrime does, which

nandez M., and Mackie I. Efficient reductions with director strings. Evolutionary Computation, 1997. SMK12. Jeremy Stober, Risto Miikkulainen, and Benjamin Kuipers. Learning geometry from sensorimo- tor experience. In Proceedings of the First Joint Conference on Development and Learning and Epigenetic Robotics,

to learn procedures that will maxi- mize some Goal whose Truth Value is estimated via an expected reward calculation (where "reward" may mean simply the Truth Value of some Atom defined as "reward"). Goal-driven learning is more general than reinforcement learning as thus defined; and the learning that CogPrime does, which

rd, 2004. Min88. Marvin Minsky. The Society of Mind. MIT Press. 1988. Min07. Marvin Minsky. The Emotion Machine. 2007. MK07. Joseph Modayil and Benjamin Kuipers. Autonomous development of a grounded object ontology by a learning robot. AAAI-07, 2007. MK08. Jonathan Mugan and Benjamin Kuipers. Towards the a

to learn procedures that will maxi- mize some Goal whose Truth Value is estimated via an expected reward calculation (where *reward” may mean simply the Truth Value of some Atom defined as ”reward”). Goal-driven learning is more general than reinforcement learning as thus defined; and the learning that CogPrime does, which is

e. Bradford, 2004. in88. Marvin Minsky. The Society of Mind. MIT Press, 1988. inO7. Marvin Minsky. The Emotion Machine. 2007. KO7. Joseph Modayil and Benjamin Kuipers. Autonomous development of a grounded object ontology by a learning robot. AAAI-07, 2007. KO08. Jonathan Mugan and Benjamin Kuipers. Towards the appl