Probing for Consciousness in Machines

TL;DR

This paper investigates whether reinforcement learning agents in virtual environments can develop basic self and world models, providing insights into the potential emergence of machine consciousness based on Damasio's theory.

Contribution

It demonstrates that RL-trained agents can form rudimentary self and world models, advancing understanding of artificial consciousness development.

Findings

Agents develop preliminary self and world models.

Probes can predict agent's position from neural activations.

Supports pathway toward machine consciousness.

Abstract

This study explores the potential for artificial agents to develop core consciousness, as proposed by Antonio Damasio's theory of consciousness. According to Damasio, the emergence of core consciousness relies on the integration of a self model, informed by representations of emotions and feelings, and a world model. We hypothesize that an artificial agent, trained via reinforcement learning (RL) in a virtual environment, can develop preliminary forms of these models as a byproduct of its primary task. The agent's main objective is to learn to play a video game and explore the environment. To evaluate the emergence of world and self models, we employ probes-feedforward classifiers that use the activations of the trained agent's neural networks to predict the spatial positions of the agent itself. Our results demonstrate that the agent can form rudimentary world and self models, suggesting a pathway toward developing machine consciousness. This research provides foundational insights into the capabilities of artificial agents in mirroring aspects of human consciousness, with implications for future advancements in artificial intelligence.