Epstein Secrets

reinforcement learning mode, to learn small programs that will guide the virtual parrot in achieving its goals (where its goals are managed via the OpenPsi motivational system inside OpenCog, loosely inspired by Joscha Bach's MicroPsi system). • Use of ECAN to learn associational relationships between

aining to the game world in which it exists (the work proposed here will involve very simple English, at the level of high-functioning parrots like Pepperberg's Alex; a subsequent project could then aim at the "toddler level".) Broadly speaking, to meaningfully explore and evaluate the value obtainable vi

reinforcement learning mode, to learn small programs that will guide the virtual parrot in achieving its goals (where its goals are managed via the OpenPsi motivational system inside OpenCog, loosely inspired by Joscha Bach's MicroPsi system). • Use of ECAN to learn associational relationships between

aining to the game world in which it exists (the work proposed here will involve very simple English, at the level of high-functioning parrots like Pepperberg's Alex; a subsequent project could then aim at the "toddler level".) Broadly speaking, to meaningfully explore and evaluate the value obtainable vi

werful tools that Joscha and I have built over the last years), and > aim to scientifically validate our approach (a subset of OpenCog, > including OpenPsi which is modeled on Joscha' Psi/MicroPsi model and > which Joscha would like to help evolve further) in the context of a > virtual animal.... Speci

ns about its virtual environment and (without hacking specifically > for the tests) performs on these tests similarly to a real parrot like > Irene Pepperberg's Alex. > Due partly to Joscha's influence, this is more science-oriented and > less engineering-oriented than my prior proposals to you, but > ne