W10. Learning 01
Today is our first module on learning, and we will start from the systemic perspective. We will learn about evolutionary algorithms and genetic programming. These kinds of algorithms both take inspiration from biology and the theory of evolution, where agents have deterministic programs once they are "born", but each new generation has a small chance of "mutation". To decide which agents and algorithms "live" to the next generation, we have to impose evaluation frameworks that simulate living, dying, gaining energy and losing energy.
Pre-readings and Videos
These articles explain how to apply evolutionary algorithms to Conway's Game of Life. They are also excellent demonstrations on how to extend Conway's Game of Life and characterize the results.
- Evolving Cellular Automata
- [Analysing Emergent Dynamics of Evolving Computation in 2D Cellular Automata] https://link.springer.com/content/pdf/10.1007/978-3-030-34500-6_1.pdf
Summary of the Day
TK.
Class notes. Available here
Learning Goals
- Describe evolutionary algorithms and genetic programming on a high level.
- Apply an evolutionary approach to simple robot tasks.
- Reason about goal-setting for agents that evolve.