RUS  ENG
Full version
JOURNALS // Avtomatika i Telemekhanika // Archive

Avtomat. i Telemekh., 2022 Issue 6, Pages 24–37 (Mi at15974)

This article is cited in 4 papers

ADAM: a model of artificial psyche

S. A. Shumskii

Moscow Institute of Physics and Technology, Dolgoprudnyi, Moscow oblast, 141701 Russia

Abstract: An ADAM artificial psyche model implementing a hierarchical deep reinforcement learning architecture is proposed. ADAM is able to learn increasingly complex and time-consuming behavioral skills as the number of artificial psyche control levels increases. Purposeful behavior is formed by a hierarchical learning system with a gradual increase in the number of levels, where each hierarchical level is responsible for its own time scale of behavior.

Keywords: general artificial intelligence, deep reinforcement learning, hierarchical control system.

Presented by the member of Editorial Board: O. P. Kuznetsov

Received: 31.10.2021
Revised: 21.01.2022
Accepted: 26.01.2022

DOI: 10.31857/S0005231022060034


 English version:
Automation and Remote Control, 2022, 83:6, 847–856


© Steklov Math. Inst. of RAS, 2024