навчання з підкріпленням

The article explores a hybrid framework for autonomous penetration testing that integrates Large Language Models (LLMs) with Markov decision processes (MDP/POMDP) and reinforcement learning (RL). Conventional penetration testing is increasingly insufficient for modern, complex cyber threats. LLMs are utilized for high-level strategic planning, generating potential attack paths, while MDP/POMDP models combined with RL execute low-level actions under uncertainty. A feedback loop allows outcomes to refine strategies in dynamic and partially observable environments.

This article presents a comprehensive study of a control model for legged robotic platforms, particularly hexapods, based on the application of deep reinforcement learning techniques. The relevance of employing artificial neural networks to form adaptive robot behavior in undefined conditions is substantiated, enabling greater flexibility and robustness in dynamic environments.

The problem of organizing data collection processes in autonomous distributed systems has been considered, in particular, in autonomous mobile cyber-physical systems and autonomous distributed environmental monitoring systems. A model of decentralized control of adaptive data collection processes based on the principle of equilibrium has been proposed. Using this model, the problem of coordinating joint collective actions of adaptive data collection processes is studied from the point of view of finding an effective scheme for their complementarity in the absence of a control center.