Evolutionary Self-Replication as a Mechanism for Producing Artificial Intelligence
arXiv:2109.08057
Abstract
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.
References in corpus (9)
- Distributed Prioritized Experience Replay
- Illuminating search spaces by mapping elites
- Agent57: Outperforming the Atari Human Benchmark
- Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
- AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
- Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
- Fully Parameterized Quantile Function for Distributional Reinforcement Learning
- Ecological Reinforcement Learning
- Near-Term Self-replicating Probes -- A Concept Design