Prediction in RALPH-MEA
Prediction in RALPH-MEA
There are various types of knowledge kept
in this architecture. Some of them are: knowledge about possible
next states that will follow a given action, and knowledge about the
utility of the next state, etc. These types of knowledge about the
world are, in fact, rules that help the architecture predict how the
environment will behave; either by itself or as a result of the
agent's actions. Prediction is facilitated by the Markov assumption.
Return to the top of this architecture.
Go to a discussion of this capability
for multiple architectures.
Current Location: RALPH-MEA - Capabilities - Prediction