We propose Quality Evolvability ES, a method that simultaneously optimizes for task performance and evolvability and without this restriction.
Neural Cellular Automata (NCAs) have been proven effective in simulating morphogenetic processes, the continuous construction of complex structures from very few starting cells.
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.