Play Style Identification Using Low-Level Representations of Play Traces in MicroRTS
This work addresses the need for adaptive game experiences and improved AI agents in gaming, though it is incremental as it builds on prior methods by reducing reliance on domain expertise.
The study tackled the problem of identifying play styles in game playing agents by using unsupervised CNN-LSTM autoencoder models to derive latent representations directly from low-level play trace data in MicroRTS, resulting in a meaningful separation of different agents in the latent space and enabling exploration of diverse play styles.
Play style identification can provide valuable game design insights and enable adaptive experiences, with the potential to improve game playing agents. Previous work relies on domain knowledge to construct play trace representations using handcrafted features. More recent approaches incorporate the sequential structure of play traces but still require some level of domain abstraction. In this study, we explore the use of unsupervised CNN-LSTM autoencoder models to obtain latent representations directly from low-level play trace data in MicroRTS. We demonstrate that this approach yields a meaningful separation of different game playing agents in the latent space, reducing reliance on domain expertise and its associated biases. This latent space is then used to guide the exploration of diverse play styles within studied AI players.