Abstract
The paper explores a selectionist approach for the autonomous acquisition of new behavior by a robot as it is attempting to stay viable in an ecosystem in which there are increasing pressures. The approach is based on a random exploration and subsequent selection of possible couplings between sensory quantities, actuator quantities, and internal motivational states. The paper gives some examples of behavioral acquisition from simulation experiments.
Full Text
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call