Abstract
In this paper a unified learning and decision making framework for artificial general intelligence (AGI) based on modern control theory is presented. The framework, called AGI Brain, considers intelligence as a form of optimality and tries to duplicate intelligence using a unified strategy. AGI Brain benefits from powerful modelling capability of state-space representation, as well as ultimate learning ability of the neural networks. The model emulates three learning stages of human being for learning its surrounding world. The model was tested on three different continuous and hybrid (continuous and discrete) Action/State/Output/Reward (ASOR) space scenarios in deterministic single-agent/multi-agent worlds. Successful simulation results demonstrate the multi-purpose applicability of AGI Brain in deterministic worlds.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Although the describing equations of the first and the second scenario are available, AGI Brain considers them as unknown environments, and from the observations that are gathered by interaction with these unknown environments, it builds their models in its memories and then completes its required tasks based on the models.
References
Wang, P.: Artificial General Intelligence, A gentle introduction, [Online]. https://sites.google.com/site/narswang/home/agi-introduction. Accessed Jan 2019
Paraskevopoulos, P.: Modern Control Engineering. Taylor & Francis Group, Didcot (2002)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge (2018)
Wulf, G.: Attention and Motor Skills Learning. Human Kinetics, Champaign (2007)
Strannegard, C., Svangard, N., Lindstrom, D., Bach, J., Steunebrick, B.: Learning and decision making in artificial animals. J. Artif. Gen. Intell. 9(1), 55–82 (2018)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Alidoust, M. (2019). AGI Brain: A Learning and Decision Making Framework for Artificial General Intelligence Systems Based on Modern Control Theory. In: Hammer, P., Agrawal, P., Goertzel, B., Iklé, M. (eds) Artificial General Intelligence. AGI 2019. Lecture Notes in Computer Science(), vol 11654. Springer, Cham. https://doi.org/10.1007/978-3-030-27005-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-27005-6_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27004-9
Online ISBN: 978-3-030-27005-6
eBook Packages: Computer ScienceComputer Science (R0)