Probing for consciousness in machines.

Artificial agents trained via reinforcement learning in a virtual environment can develop rudimentary forms of world and self models, which are key components of core consciousness as defined by Antonio Damasio. The agent learned to play a video game and explore its environment; probes—feedforward classifiers—used the agent's neural network activations to predict the agent's spatial position. Results demonstrate that the agent formed preliminary world and self models, suggesting a pathway toward machine consciousness. This provides foundational insights into artificial agents mirroring aspects of human consciousness.

Study at a glance

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.