Learning rate in the reinforcement learning method for unknown location targets searching system

Albrekht, Y.; Pysarenko, A.

Learning rate in the reinforcement learning method for unknown location targets searching system

Файли

278916-643490-1-10-20230514.pdf (402.36 KB)

Дата

2023

Автори

Albrekht, Y.

Pysarenko, A.

Видавець

КПІ ім. Ігоря Сікорського

Анотація

The article explores the dependence of the system learning rate on the number of mutually independent modules in the reinforcement learning method. The study defines an environment with two types of objects that bring points to the final score and uses Deep Q Learning algorithms with 36 input data and 5 possible outcomes to conduct the experiment. The goal is to determine the optimal number of objects for which the use of reinforcement learning will give the best result for the same number of iterations. The research is part of a solution to the problem of creating a drone flock control system to find the position of objects in an unknown area.

Ключові слова

reinforcement learning, mutually independent modules, Deep Q Learning

Бібліографічний опис

Albrekht, Y. Learning rate in the reinforcement learning method for unknown location targets searching system / Y. Albrekht, A. Pysarenko // Адаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник. – 2023. – № 1 (42). – С. 3-8. – Бібліогр.: 5 назв.