Abstract—What is consciousness? Many definitions have
been proposed to describe this concept. Our research aims to
achieve consciousness in computers and, in particular, focuses
on a decision-making system based on consciousness. After the
requirements are defined, a system that satisfies these conditions
is proposed. Especially, this work proposes a new
decision-making system based on consciousness. This model
consists of emotional memories, declarative memories, and an
amygdala-like mediation component incorporating three types
of modules such as agilor, contemplator, and mediator. The
effectiveness of the proposed system is validated through
numerical experiments.
Index Terms—Consciousness system, exploitation-oriented
learning (XoL), reinforcement learning.
Kazuteru Miyazaki is with the National Institution for Academic Degrees
and University Evaluation, 1-29-1 Gakuen-nishimachi Kodaira-shi, Tokyo
187-8587 Japan (e-mail: teru@niad.ac.jp).
Cite: Kazuteru Miyazaki, "Proposed Decision-Making System Based on Consciousness in Multiple Rewards and Penalties Environments," International Journal of Machine Learning and Computing vol. 5, no. 2, pp. 121-126, 2015.