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

, ImplicationLink, etc.) or a fuzzy value (as in MemberLink, EvaluationLink). • Strong Self-Modification: This is generally used as synonymous with Self-Modification, in a CogPrime context. • Subsymbolic: Involving processing of data using elements that have no correspondence to natural language terms, nor abst

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

cision graph looks like: Input: List L Output: List If ( P1 (L) ) N1(L) Else If ( P2 (L) ) N2 (L) Else If ( Pk (L) ) Nk(L) EFTA00624098 18.4 Self-Modification via Theorem-Proving 323 where the Pi are predicates, and the Ni are schemata corresponding to other nodes of the decision graph (children of the c

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

nt decision graphs. The decision graph leading to maximal optimization, may not be the one that leads CogPrime cognition in optimal directions. 18.4 Self-Modification via Theorem-Proving Supercompilation is a potentially very valuable tool for self-modification. If one wants to take an existing schema and graduall