Epstein Secrets

that is relatively simple, yet still intuitively rich and meaningful. Toward that end, the context of

ntend our virtual parrot to do. A high level depiction of some of the learning that would be expected to occur in this case is given in Diagram 2. Program Learning (MOSES) Learns procedure to "get food from a difficult spot using a Wier Sends procedure to PLN for further learning. The action "pick up stick" w

that is relatively simple, yet still intuitively rich and meaningful. Toward that end, the context of

ntend our virtual parrot to do. A high level depiction of some of the learning that would be expected to occur in this case is given in Diagram 2. Program Learning (MOSES) Learns procedure to "get food from a difficult spot using a stick" Sends procedure to PLN for further learning. The action "pick up stick-

29.7 Conclusion 189 flexibly interacting with a rich stream of data from the everyday human world. Thi

vations regarding the implications of this choice for procedure learning, and the formal representation of procedure learning with CogPrime. 30.1.1 Program Learning An optimization problem may be defined as follows: a solution space S is specified, together with some fitness function on solutions, where "solvin