Clustering Player Strategies from Variable-Length Game Logs in Dominion
This work addresses the challenge of understanding player strategies in games with variable-length logs, offering a domain-specific tool for game analysis.
The paper tackled the problem of analyzing player strategies in the card game Dominion by encoding variable-length game logs into numeric features and applying t-SNE for visualization, resulting in intuitive visual representations that capture qualitative differences in strategies as rays from the starting state.
We present a method for encoding game logs as numeric features in the card game Dominion. We then run the manifold learning algorithm t-SNE on these encodings to visualize the landscape of player strategies. By quantifying game states as the relative prevalence of cards in a player's deck, we create visualizations that capture qualitative differences in player strategies. Different ways of deviating from the starting game state appear as different rays in the visualization, giving it an intuitive explanation. This is a promising new direction for understanding player strategies across games that vary in length.