| Issue |
ITM Web Conf.
Volume 59, 2024
II International Workshop “Hybrid Methods of Modeling and Optimization in Complex Systems” (HMMOCS-II 2023)
|
|
|---|---|---|
| Article Number | 04006 | |
| Number of page(s) | 5 | |
| Section | Adaptive Intelligence: Exploring Learning in Evolutionary Algorithms and Neural Networks | |
| DOI | https://doi.org/10.1051/itmconf/20245904006 | |
| Published online | 25 January 2024 | |
Functional structure of reflexive-active systems of artificial heterogeneous intelligent agents
Kaliningrad Branch of the Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences,
5 Gostinaya Str, Kaliningrad 236022, Russian Federation
* Corresponding author: ser-list-post@yandex.ru
The paper is aimed at developing distributed artificial intelligence systems for relevant simulation of collective solving of practical problems by modeling reflection. The paper presents the basic design principles and typical functional structure of reflexive-active systems of artificial heterogeneous intelligent agents. Agents of such systems mutually model each other’s reflexive positions; dynamically develop tactics and strategies for their behavior that are relevant to the models of their counterparties; if it is necessary during problem solving, attract new agents from the pool of available agents built by various developers and exclude existing ones, rebuilding “on the fly” the composition of agents and the structure of connections between them.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.