We set out to compare the utility of different representations of driving simulator time series data in the context of both supervised and unsupervised learning algorithms. Given the task of identifying similar time series; it is important to understand how a dataset of time series samples might be distributed and how effectively different methods capture the groupings of distinct behaviors. First we engineer three representations of the driving simulator data: converting them to feature vectors, using the raw time series, and rendering them as images. At which point, we introduce a novel method for comparing time series using temporal and spatial alignments. Then, we employ a battery of clustering algorithms to isolate groups of samples with similar traits and evaluate the quality of clusters produced. We also explore the performance of k-NN classifiers using the different dissimilarity measures resulting from these representations.

A significant amount of work has advocated that Learning from Demonstration (LfD) is a promising approach to allow end-users to create behaviors for in-game characters without requiring programming. However, one major problem with this approach is that many LfD algorithms require large amounts of training data, and thus are not practical for learning from human demonstrators. In this paper, we focus on LfD with limited training data, and specifically on the problem of active LfD where the demonstrators are human. We present the results of a user study in comparing SALT, a new active LfD approach, versus a previous state-of-the-art Active LfD algorithm, showing that SALT significantly outperforms it when learning from a limited amount of data in the context of learning to play a puzzle video game.

This paper focuses on tracing player knowledge in educational games. Specifically, given a set of concepts or skills required to master a game, the goal is to estimate the likelihood with which the current player has mastery of each of those concepts or skills. The main contribution of the paper is an approach that integrates machine learning and domain knowledge rules to find when the player applied a certain skill and either succeeded or failed. This is then given as input to a standard knowledge tracing module (such as those from Intelligent Tutoring Systems) to perform knowledge tracing. We evaluate our approach in the context of an educational game called Parallel to teach parallel and concurrent programming with data collected from real users, showing our approach can predict students skills with a low mean-squared error.

This paper describes a game prototype called "SHRDLU" that explores the concept of designing a game around the ideas behind Winograd's original SHRDLU system. We briefly describe the main gameplay, as well as the natural language and inference architecture used by game NPCs.

The 13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE 2017) was held at the Snowbird Ski and Summer Resort in Little Cottonwod Canyon in the Wasatch Range of the Rock Mountains near Salt Lake County, Utah. Along with the main conference presentations, the meeting included two tutorials, three workshops, and invited keynotes. This report summarizes the main conference. It also includes contributions from the organizers of the three workshops.

A significant amount of work has advocated that Learning from Demonstration (LfD) is a promising approach to allow end-users to create behaviors for in-game characters without requiring programming. However, one major problem with this approach is that many LfD algorithms require large amounts of training data, and thus are not practical. In this paper, we focus on LfD with limited training data, and specifically on the problem of Active Learning from Demonstration in settings where the amount of data that can be queried from the demonstrator is limited by a predefined budget. We extend our novel Active Learning from Demonstration approach, SALT, and compare it to related LfD algorithms in both task performance (reward) and similarity to the demonstrator's behavior, when used with relatively small amounts of training data. We use Super Mario Bros. and two variations of the Thermometers puzzle game as our evaluation domains.

Detection of abnormal behavior is the catalyst for many applications that seek to react to deviations from behavioral expectations. However, this is often difficult to do when direct communication with the performer is impractical. Therefore, we propose to create models of normal human performance and then compare their performance to a human's actual behavior. Any detected deviations can be then used to determine what condition(s) could possibly be influencing the deviant behavior. We build the models of human behavior through machine learning from observation; more specifically, we employ the Genetic Context Learning algorithm to create models of normal car driving behaviors of different humans with and without ADHD (Attention Deficit Hyperactivity Disorder). We use a car simulator for our studies to eliminate risk to our test subjects and to other drivers. Our results show that different driving situations have varying utility in abnormal behavior detection. Learning from Observation was successful in building models to be applied to abnormal behavior detection.

This article presents the results of the first edition of the microRTS (μRTS) AI competition, which was hosted by the IEEE Computational Intelligence in Games (CIG) 2017 conference. The goal of the competition is to spur research on AI techniques for real-time strategy (RTS) games. In this first edition, the competition received three submissions, focusing on address- ing problems such as balancing long-term and short-term search, the use of machine learning to learn how to play against certain opponents, and finally, dealing with partial observability in RTS games.

Distributions over rankings are used to model user preferences in various settings including political elections and electronic commerce. The Repeated Insertion Model (RIM) gives rise to various known probability distributions over rankings, in particular to the popular Mallows model. However, probabilistic inference on RIM is computationally challenging, and provably intractable in the general case. In this paper we propose an algorithm for computing the marginal probability of an arbitrary partially ordered set over RIM. We analyze the complexity of the algorithm in terms of properties of the model and the partial order, captured by a novel measure termed the "cover width." We also conduct an experimental study of the algorithm over serial and parallelized implementations. Building upon the relationship between inference with rank distributions and counting linear extensions, we investigate the inference problem when restricted to partial orders that lend themselves to efficient counting of their linear extensions.

This paper defines a learning algorithm for plan grammars used for plan recognition. The algorithm learns Combinatory Categorial Grammars (CCGs) that capture the structure of plans from a set of successful plan execution traces paired with the goal of the actions. This work is motivated by past work on CCG learning algorithms for natural language processing, and is evaluated on five well know planning domains.