Abstract:
The purpose of the study is to study the possibilities of multi-generational optimization of
control systems based on multi-agent neurocognitive architectures to create general artificial intelligence
agents capable of independently solving a universal range of tasks in a real environment. The main
principles for achieving the adaptive stability of general artificial intelligence agents based on multi-agent
neurocognitive architectures to the operating conditions based on ontophylogenetic learning in the process
of synthesis of problem solving over dynamic decision trees are developed. The basic principles for
constructing algorithms for multi-generational optimization of the structural and functional organization
of general artificial intelligence agents based on multi-agent neurocognitive architectures, taking into
account genetic, ontological and social factors, have been developed.