Simulating evolution with reinforcement learning

Hundreds of millions of years of evolution have blessed our planet with a wide variety of lifeforms, each intelligent in its own fashion. Each species has evolved to develop innate skills, learning capacities, and a physical form that ensure its survival in its environment.

But despite being inspired by nature and evolution, the field of artificial intelligence has largely focused on creating the elements of intelligence separately and fusing them together after development. While this approach has yielded great results, it has also limited the flexibility of AI agents in some of the basic skills found in even the simplest lifeforms.

In a new paper published in the scientific journal Nature, AI researchers at Stanford University present a new technique that can help take steps toward overcoming some of these limits. Titled “Deep Evolutionary Reinforcement Learning,” the new technique uses a complex virtual environment and reinforcement learning to create virtual agents that can evolve both in their physical structure and learning capacities. The findings can have important implications for the future of AI and robotics research.

Read the full analysis on TechTalks.

For more on AI research:

• Can AI learn to reason about the world like children?

• The dos and don’ts of machine learning research

• Google’s new deep learning system can give a boost to radiologists