Artificial agents trained via reinforcement learning can develop rudimentary forms of self and world models—key components of core consciousness as defined by Antonio Damasio. In a virtual environment, an agent learning to play a video game formed internal representations that allowed probes (feedforward classifiers) to predict the agent's spatial position from its neural activations. These results suggest that machine consciousness may be possible as a byproduct of goal-directed learning, offering foundational insights for AI development.
Whether machines could become self-aware is a longstanding philosophical question, but self-awareness cannot be observed externally, and distinguishing genuine consciousness from clever imitation requires access to inner workings. Examining common machine learning approaches reveals that many important algorithmic steps toward machines with a core consciousness have already been taken.