Ultimate is a sport where points are scored by passing a disc and catching it in the opposing team's end zone. In Ultimate, the player holding the disc cannot move, making field dynamics primarily driven by other players' movements. However, current literature in team sports has ignored quantitative evaluations of when players initiate such unlabeled movements in game situations. In this paper, we propose a quantitative evaluation method for movement initiation timing in Ultimate Frisbee. First, game footage was recorded using a drone camera, and players' positional data was obtained, which will be published as UltimateTrack dataset. Next, players' movement initiations were detected, and temporal counterfactual scenarios were generated by shifting the timing of movements using rule-based approaches. These scenarios were analyzed using a space evaluation metric based on soccer's pitch control reflecting the unique rules of Ultimate. By comparing the spatial evaluation values across scenarios, the difference between actual play and the most favorable counterfactual scenario was used to quantitatively assess the impact of movement timing. We validated our method and show that sequences in which the disc was actually thrown to the receiver received higher evaluation scores than the sequences without a throw. In practical verifications, the higher-skill group displays a broader distribution of time offsets from the model's optimal initiation point. These findings demonstrate that the proposed metric provides an objective means of assessing movement initiation timing, which has been difficult to quantify in unlabeled team sport plays.

Recent advances in game informatics have enabled us to find strong strategies across a diverse range of games. However, these strategies are usually difficult for humans to interpret. On the other hand, research in Explainable Artificial Intelligence (XAI) has seen a notable surge in scholarly activity. Interpreting strong or near-optimal strategies or the game itself can provide valuable insights. In this paper, we propose two methods to quantify the feature importance using Shapley values: one for the game itself and another for individual AIs. We empirically show that our proposed methods yield intuitive explanations that resonate with and augment human understanding.

While neural networks demonstrate a remarkable ability to model linguistic content, capturing contextual information related to a speaker's conversational role is an open area of research. In this work, we analyze the effect of speaker role on language use through the game of Mafia, in which participants are assigned either an honest or a deceptive role. In addition to building a framework to collect a dataset of Mafia game records, we demonstrate that there are differences in the language produced by players with different roles. We confirm that classification models are able to rank deceptive players as more suspicious than honest ones based only on their use of language. Furthermore, we show that training models on two auxiliary tasks outperforms a standard BERT-based text classification approach. We also present methods for using our trained models to identify features that distinguish between player roles, which could be used to assist players during the Mafia game.

Even when machine learning systems surpass human ability in a domain, there are many reasons why AI systems that capture human-like behavior would be desirable: humans may want to learn from them, they may need to collaborate with them, or they may expect them to serve as partners in an extended interaction. Motivated by this goal of human-like AI systems, the problem of predicting human actions -- as opposed to predicting optimal actions -- has become an increasingly useful task. We extend this line of work by developing highly accurate personalized models of human behavior in the context of chess. Chess is a rich domain for exploring these questions, since it combines a set of appealing features: AI systems have achieved superhuman performance but still interact closely with human chess players both as opponents and preparation tools, and there is an enormous amount of recorded data on individual players. Starting with an open-source version of AlphaZero trained on a population of human players, we demonstrate that we can significantly improve prediction of a particular player's moves by applying a series of fine-tuning adjustments. The differences in prediction accuracy between our personalized models and unpersonalized models are at least as large as the differences between unpersonalized models and a simple baseline. Furthermore, we can accurately perform stylometry -- predicting who made a given set of actions -- indicating that our personalized models capture human decision-making at an individual level.

Procedural content generation (PCG) has recently become one of the hottest topics in computational intelligence and AI game researches. Among a variety of PCG techniques, search-based approaches overwhelmingly dominate PCG development at present. While SBPCG leads to promising results and successful applications, it poses a number of challenges ranging from representation to evaluation of the content being generated. In this paper, we present an alternative yet generic PCG framework, named learning-based procedure content generation (LBPCG), to provide potential solutions to several challenging problems in existing PCG techniques. By exploring and exploiting information gained in game development and public beta test via data-driven learning, our framework can generate robust content adaptable to end-user or target players on-line with minimal interruption to their experience. Furthermore, we develop enabling techniques to implement the various models required in our framework. For a proof of concept, we have developed a prototype based on the classic open source first-person shooter game, Quake. Simulation results suggest that our framework is promising in generating quality content.