Sciweavers

Share
TSMC
2002

The STAR automaton: expediency and optimality properties

9 years 10 months ago
The STAR automaton: expediency and optimality properties
Abstract--We present the STack ARchitecture (STAR) automaton. It is a fixed structure, multiaction, reward-penalty learning automaton, characterized by a star-shaped state transition diagram. Each branch of the star contains states associated with a particular action. The branches are connected to a central "neutral" state. The most general version of STAR involves probabilistic state transitions in response to reward and/or penalty, but deterministic transitions can also be used. The learning behavior of STAR results from the stack-like operation of the branches; the learning parameter is . By mathematical analysis, it is shown that STAR with deterministic reward/probabilistic penalty and a sufficiently large can be rendered -optimal in every stationary environment. By numerical simulation it is shown that in nonstationary, switching environments, STAR usually outperforms classical variable structure automata such as , , and .
Anastasios A. Economides, Athanasios Kehagias
Added 23 Dec 2010
Updated 23 Dec 2010
Type Journal
Year 2002
Where TSMC
Authors Anastasios A. Economides, Athanasios Kehagias
Comments (0)
books