Starcraft II is a popular real-time strategy (RTS) game, in which players compete with each other online. Based on their performance, the players are ranked in one of seven leagues. In our research, we aim at constructing a player model that is capable of predicting the league in which a player competes, using observations of their in-game behavior. Based on cognitive research and our knowledge of the game, we extracted from 1297 game replays a number of features that describe skill. After a preliminary test, we selected the SMO classifier to construct a player model, which achieved a weighted accuracy of 47.3% (SD 2.2). This constitutes a significant improvement over the weighted baseline of 25.5% (SD 1.1). We tested from what moment in the game it is possible to predict a player's skill, which we found is after about 2.5 minutes of gameplay, i.e., even before the players have confronted each other within the game. We conclude that our model can predict a player's skill early in the game.
In many imperfect information games, the ability to exploit the opponent is crucial for achieving high performance. For instance, skilled poker players usually capitalize on various weaknesses in their opponents' playing patterns and styles to maximize their earnings. Therefore, it is important to enable computer players in such games to identify flaws in opponent strategies and adapt their behaviors to exploit these flaws. This paper presents a genetic algorithm to evolve adaptive LSTM (Long Short Term Memory) poker players featuring effective opponent exploitation. Experimental results in heads-up no-limit Texas Hold'em demonstrate that adaptive LSTM players are able to obtain 40% to 1360% more earnings than cutting-edge game theoretic poker players against opponents with various flawed strategies. In addition, experimental results indicate that adaptive LSTM players evolved through playing against simple and weak rule-based opponents can achieve comparable performance against top game-theoretic poker players. The approach introduced in this paper is a promising start for building adaptive computer players for imperfect information games.
Wiggins, Joseph B. (University of Florida) | Kulkarni, Mayank (University of Florida) | Min, Wookhee (North Carolina State University) | Mott, Bradford (North Carolina State University) | Boyer, Kristy Elizabeth (University of Florida) | Wiebe, Eric (North Carolina State University) | Lester, James (North Carolina State University)
Player affect is a central consideration in the design of game-based learning environments. Affective indicators such as facial expressions exhibited during gameplay may support building more robust player models and adaptation modules. In game-based learning, predicting player mental demand and engagement from player affect is a particularly promising approach to helping create more effective gameplay. This paper reports on a predictive player-modeling approach that observes player affect during early interactions with a game-based learning environment and predicts selfreports of mental demand and engagement at the conclusion of gameplay sessions. The findings show that automatically detected facial expressions such as those associated with joy, disgust, sadness, and surprise are significant predictors of players' self-reported engagement and mental demand at the end of gameplay interactions. The results suggest that it is possible to create affect-based predictive player models that can enable proactively tailored gameplay by anticipating player mental demand and engagement.
Modeling player engagement is a key challenge in games. However, the gameplay signatures of engaged players can be highly context-sensitive, varying based on where the game is used or what population of players is using it. Traditionally, models of player engagement are investigated in a particular context, and it is unclear how effectively these models generalize to other settings and populations. In this work, we investigate a Bayesian hierarchical linear model for multi-task learning to devise a model of player engagement from a pair of datasets that were gathered in two complementary contexts: a Classroom Study with middle school students and a Laboratory Study with undergraduate students. Both groups of players used similar versions of Crystal Island, an educational interactive narrative game for science learning. Results indicate that the Bayesian hierarchical model outperforms both pooled and context-specific models in cross-validation measures of predicting player motivation from in-game behaviors, particularly for the smaller Classroom Study group. Further, we find that the posterior distributions of model parameters indicate that the coefficient for a measure of gameplay performance significantly differs between groups. Drawing upon their capacity to share information across groups, hierarchical Bayesian methods provide an effective approach for modeling player engagement with data from similar, but different, contexts.
Min, Wookhee (North Carolina State University) | Baikadi, Alok (University of Pittsburgh) | Mott, Bradford (North Carolina State University) | Rowe, Jonathan (North Carolina State University) | Liu, Barry (North Carolina State University) | Ha, Eun Young (IBM) | Lester, James (North Carolina State University)
Recent years have seen a growing interest in player modeling, which supports the creation of player-adaptive digital games. A central problem of player modeling is goal recognition, which aims to recognize players' intentions from observable gameplay behaviors. Player goal recognition offers the promise of enabling games to dynamically adjust challenge levels, perform procedural content generation, and create believable NPC interactions. A growing body of work is investigating a wide range of machine learning-based goal recognition models. In this paper, we introduce GOALIE, a multidimensional framework for evaluating player goal recognition models.