Open AccessDeep Learning of Adaptive Control Systems Based on a Logical-probabilistic Approach
Author(s) -
Alexander Demin,
AUTHOR_ID
Publication year - 2021
Publication title -
izvestiâ irkutskogo gosudarstvennogo universiteta. seriâ "matematika"/izvestiâ irkutskogo gosudarstvennogo universiteta. seria matematika
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.411
H-Index - 3
eISSN - 2541-8785
pISSN - 1997-7670
DOI - 10.26516/1997-7670.2021.38.65
Subject(s) - computer science , probabilistic logic , artificial intelligence , scheme (mathematics) , reinforcement learning , control (management) , logical conjunction , machine learning , selection (genetic algorithm) , mathematics , mathematical analysis , programming language
The problem of automatic selection of subgoals is currently one of the most relevant in adaptive control problems, in particular, in Reinforcement Learning. This paper proposes a logical-probabilistic approach to the construction of adaptive learning control systems capable of detecting deep implicit subgoals. The approach uses the ideas of the neurophysiological Theory of functional systems to organize the control scheme, and logical-probabilistic methods of machine learning to train the rules of the system and identify subgoals. The efficiency of the proposed approach is demonstrated by an example of solving a three-stage foraging problem containing two nested implicit subgoals