Evolutionary Computation – Part 4

evolution4

Our journey to harness the power of evolution is coming to an end. In the previous three parts of this tutorial we have constructed a bipedal body and a mutable genome that determines its behaviour. What’s left now is to actually implement the evolutionary computation that will find a successful walking strategy.

Continue reading

Evolutionary Computation – Part 3

evolution3

When we are looking at a problem through the lens of evolution, we always have to take into account its two faces: the phenotype and genotype. The previous post focused on creating the body of the creature, together with its brain. It is now time to focus on the genotype, which is the way such information is represented, transmitted and mutated.

Continue reading

Evolutionary Computation – Part 2

evolution2

In the first part of this tutorial we have explored what evolutionary computation is, and why it works. The rest of this tutorial will show how to set up a practical example and how to use evolution to solve a real problem. In our case, the problem is teaching a bipedal creature how to keep balance and how to walk effectively. Rather than evolving the body of the creature, we are interested in finding a strategy to make it walk as fast as possible.

walker_8

Continue reading

Evolutionary Computation – Part 1

evolution1

This series of tutorial is about evolutionary computation: what it is, how it works and how to implement it in your projects and games. At the end of this series you’ll be able to harness the power of evolution to find the solution to problems you have no idea how to solve. As a toy example, this tutorial will show how evolutionary computation can be used to teach a simple creature to walk. If you want to try the power of evolutionary computation directly in your browser, try Genetic Algorithm Walkers.

evolution

Continue reading