Generating RTS Game units Using Search-Based PCG and MCTS
In this EXAG 2022 presentation, Kynan Sorochan discusses how Real-Time Strategy (RTS) game unit generation is a relatively unexplored area of Procedural Content Generation (PCG) research. This leaves the question of how to generate interesting and balanced units largely unanswered. Creating unique and balanced units can be a difficult task when designing an RTS game. Having an automated method of designing units could help developers speed up the creation process as well as find new ideas. In this work they propose a method of generating and testing new units to be introduced into an RTS game. Drawing on Search-Based PCG and a fitness function based on Monte Carlo Tree Search (MCTS), their approach is capable of generating a variety of units. They present ten units generated by their system designed to be used in the game microRTS, as well as test results demonstrating that these units are unique and balanced.