Exploring the Potential of the Bicameral Mind Theory in Reinforcement Learning Algorithms
Computers · 03.06.2025 · 14 (6) · 218
DOI: 10.3390/computers14060218 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers, online erschienen am 03.06.2025. Verfasst von Munavvarkhon Mukhitdinova und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study explores the potential of Julian Jaynes’ bicameral mind theory in enhancing reinforcement learning (RL) algorithms and large language models (LLMs) for artificial intelligence (AI) systems. By drawing parallels between the dual-process structure of the bicameral mind, the observation–action cycle in RL, and the “thinking”/”writing” processes in LLMs, we hypothesize that incorporating principles from this theory could lead to more efficient and adaptive AI. Empirical evidence from OpenAI’s CoinRun and RainMazes models, together with analysis of Claude, Gemini, and ChatGPT functioning, supports our hypothesis, demonstrating the universality of the dual-component structure across different types of AI systems. We propose a conceptual model for integrating bicameral mind principles into AI architectures capable of guiding the development of systems that effectively generalize knowledge across various tasks and environments.
Zitieren
APA
Mukhitdinova, M., & Petrova, M. (2025). Exploring the Potential of the Bicameral Mind Theory in Reinforcement Learning Algorithms. Computers, 14(6), 218. https://doi.org/10.3390/computers14060218
Vancouver
Mukhitdinova M, Petrova M. Exploring the Potential of the Bicameral Mind Theory in Reinforcement Learning Algorithms. Computers. 2025;14(6):218. doi:10.3390/computers14060218
BibTeX
@article{Mukhitdinova2025,
author = {Mukhitdinova, Munavvarkhon and Petrova, Mariana},
title = {Exploring the Potential of the Bicameral Mind Theory in Reinforcement Learning Algorithms},
journal = {Computers},
year = {2025},
volume = {14},
number = {6},
pages = {218},
doi = {10.3390/computers14060218}
}
EUVIMED