Rationality in Meta-Reasoning Architectures
Rationality in Meta-Reasoning Architectures
Rationality of
MAX agents depends on the
architecture-level operators provided,
the learning mechanisms incorporated and the
substrate-level rules provided
as part of the definition of the architecture. The
architecture per se does not guarantee nor preclude rationality. The authors
point out that the architecture,
based on two-valued
logic, limits the
environments in which MAX agents can perform well and
if placed in inappropriate environments may not behave rationally.
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: Meta-Reasoning-Issues-Rationality