Discovering Meaningful Labelings for RTS Game Replays via Replay Embeddings
Real-Time Strategy (RTS) games are an interesting environment to study challenging AI problems, such as real-time adversarial planning and opponent modeling. In this paper we focus on approaches that make use of replay data, which usually encodes domain expert knowledge of gameplay. Some of these approaches use supervised learning to learn player/agent strategy models and thus rely on these replays being annotated with specific strategies or other labels. However, replays do not usually contain labels for these strategies. The problem we address in this paper is the automatic discovery of meaningful labeling of replays in RTS games. We address this problem by learning action and replay embeddings via recursive neural network models such as LSTMs. These embedded replays can then be clustered to discover labelings by using the clusters as the labels. We show that we can learn embeddings and discover labelings for replays that are correlated with meaningful information from those replays.