Evolutionary Self-Replication as a Mechanism for Producing Artificial Intelligence
This work addresses the challenge of creating AI without predefined objectives, potentially offering a novel approach for researchers in evolutionary computation and AI, though it appears incremental as it applies known evolutionary concepts to modern learning environments.
The paper tackles the problem of producing artificial intelligence by exploring self-replication and natural selection as mechanisms, showing that evolved organisms in Atari and robotic environments can generate meaningful, complex, and intelligent behavior without explicit rewards or objectives.
Can reproduction alone in the context of survival produce intelligence in our machines? In this work, self-replication is explored as a mechanism for the emergence of intelligent behavior in modern learning environments. By focusing purely on survival, while undergoing natural selection, evolved organisms are shown to produce meaningful, complex, and intelligent behavior, demonstrating creative solutions to challenging problems without any notion of reward or objectives. Atari and robotic learning environments are re-defined in terms of natural selection, and the behavior which emerged in self-replicating organisms during these experiments is described in detail.