Marti-5: A Mathematical Model of "Self in the World" as a First Step Toward Self-Awareness
This work addresses the problem of modeling self-awareness for AI researchers, but it is incremental as it builds on long-standing neuroscience concepts.
The authors tackled the lack of a mathematical model for integrating 'what' and 'where' brain pathways by proposing a biologically inspired model that separates self from environment to improve predictions, resulting in a reinforcement learning agent that successfully learns to play Atari games like Pong and Breakout.
The existence of 'what' and 'where' pathways of information processing in the brain was proposed almost 30 years ago, but there is still a lack of a clear mathematical model that could show how these pathways work together. We propose a biologically inspired mathematical model that uses this idea to identify and separate the self from the environment and then build and use a self-model for better predictions. This is a model of neocortical columns governed by the basal ganglia to make predictions and choose the next action, where some columns act as 'what' columns and others act as 'where' columns. Based on this model, we present a reinforcement learning agent that learns purposeful behavior in a virtual environment. We evaluate the agent on the Atari games Pong and Breakout, where it successfully learns to play. We conclude that the ability to separate the self from the environment gives advantages to the agent and therefore such a model could appear in living organisms during evolution. We propose Self-Awareness Principle 1: the ability to separate the self from the world is a necessary but insufficient condition for self-awareness.