Re: Goal of AI: Perfect or Bounded Rationality

Curt,

Would you subscribe to the proposition that there exists:

1. A reinforcement learning algorithm
2. A set of conditional reinforcements (possibly non-stationary)
3. A sequence of sensory input

such that a machine which learns according to the above would exhibit
behavior
indistiguishable from human behavior? Or are there behaviors that
humans exhibit
which will cannot be accounted for by reinforcement learning alone?

.

Relevant Pages

  • Re: consciousness, was Re: etc.
    ... of motivations, where they come from, how they evolve with time. ... machine which duplicate human behavior, but I haven't seen anything from ... by the same fundamental process of reinforcement learning. ...
    (comp.ai.philosophy)
  • Re: What is innate and how can we determine it?
    ... of reinforcement learning. ... If we train a dog to shake, is that an example of the intelligent beahvior ... Isn't the point of AI to be able to duplicate human behavior in a machine? ... If your machine is unable to get the "stupid" beahviors the same, ...
    (comp.ai.philosophy)