AI Article Synopsis
- A model is introduced that features learning automata making decisions in stochastic games at two distinct levels: high-level for selecting the game environment and low-level for action selection within that environment.
- Both decision levels are influenced by information delays stemming from inherent latencies and sluggish updates of state changes.
- Analysis includes simulations that demonstrate consistency with expected behavior for small step lengths, while findings also indicate that the system shows chaotic behavior with very small penalty parameters, as evidenced by a Feigenbaum diagram and computations of Lyapunov exponents.
Article Abstract
A model is presented of learning automata playing stochastic games at two levels. The high level represents the choice of the game environment and corresponds to a group decision. The low level represents the choice of action within the selected game environment. Both of these decision processes are affected by delays in the information state due to inherent latencies or to the delayed broadcast of state changes. Analysis of the intrinsic properties of this Markov process is presented along with simulated iterative behavior and expected iterative behavior. The results show that simulation agrees with expected behavior for small step lengths in the iterative map. A Feigenbaum diagram and numerical computation of the Lyapunov exponents show that, for very small penalty parameters, the system exhibits chaotic behavior.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/3477.764864 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!