Neuroevolution, or optimization of neural networks through evolutionary computation, is a method for constructing intelligent agents through population-based search. It is particularly useful in partially observable domains with sparse and multiobjective reinforcement; compared to other policy search techniques, its power comes from extensive exploration that allows it to find effective, often surprising solutions. Prime application domains include robotic control, game-playing agents, and decision-making. More recently it has also been extended to optimizing deep-learning architectures, understanding how biological intelligence evolved, and optimizing neural networks for hardware implementation. It can also be used synergistically with reinforcement learning and LLMs, adding an element of exploration to those techniques. The tutorial introduces participants to neuroevolution fundamentals, progresses to several advanced topics that make neuroevolution effective and general, reviews example application areas, and proposes further research questions. It is accompanied by a hands-on exercise that makes the concepts concrete and allows the participants to take advantage of neuroevolution immediately.
(1) Neuroevolution for control
(2) Evolutionary Model Merging
(3) Quality Diversity for Model Merging.
Instructions are given in the notebook.