Versatility of Homer
Versatility of Homer
The class of possible tasks for a basic agent seems rich, assuming the
simulated robotic manipulation. Goal
specification seems limited by the expressiveness of the state transition
semantics, but this representation seems rich enough to handle most
real-world goals, including those concerning physical and temporal events.
The use of episodic memory also adds
to the variety of possible behaviors, since the agent is partially molded
by its experiences.
There is also the question of extending Homer's mechanisms in the real-world
rather than its
simulated world.
Currently, all basic agent sensing and manipulation takes place
on the simulator. Whenever simulators are used, the results are highly
sensitive to the accuracy of the model. It is difficult to extend simulated
results to behavior in the real world, so this problem will remain until
Homer actually has an opportunity to operate in the ocean.
Return to the Issues Index for this Architecture.
Return to the top of this architecture.
Go to a Discussion of this
issue for multiple architectures.
Current Location: Homer-Issues-Versatility