Quality Evolvability ES: Evolving Individuals With a Distribution of Well Performing and Diverse Offspring

1 code implementation • 19 Mar 2021 • Adam Katona, Daniel W. Franks, James Alfred Walker

We propose Quality Evolvability ES, a method that simultaneously optimizes for task performance and evolvability and without this restriction.

Growing 3D Artefacts and Functional Machines with Neural Cellular Automata

1 code implementation • 15 Mar 2021 • Shyam Sudhakaran, Djordje Grbic, Siyan Li, Adam Katona, Elias Najarro, Claire Glanois, Sebastian Risi

Neural Cellular Automata (NCAs) have been proven effective in simulating morphogenetic processes, the continuous construction of complex structures from very few starting cells.

Time to Die: Death Prediction in Dota 2 using Deep Learning

1 code implementation • 21 May 2019 • Adam Katona, Ryan Spick, Victoria Hodge, Simon Demediuk, Florian Block, Anders Drachen, James Alfred Walker

Even though death events are rare within a game (1\% of the data), the model achieves 0. 377 precision with 0. 725 recall on test data when prompted to predict which of any of the 10 players of either team will die within 5 seconds.

Dota 2