Scalability of Homer
Scalability of Homer
The episodic memory would seem to
face a utility
problem, since its learning is reflexive. There is a passing mention
of a "forgetting" capability, but it is not discussed. Without such a
mechanism, the agent's experiences would pile up, making it difficult for
the planner to find previous
solutions relevant to its current problem. Currently, the designers make an
explicit effort to keep the agent's lifespan short to prevent the slowdown.
In addition, the use of dual representations in the lexipedia and the generic memory requires twice as much
space, which can cause problems for an agent of limited resources.
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-Scalability