Games have played a prominent role as a test-bed for advancements in the field of Artificial Intelligence ever since its foundation over half a century ago, resulting in highly specialized world-class game-playing systems being developed for various games. The establishment of the International General Game Playing Competition in 2005, however, resulted in a renewed interest in more general problem solving approaches to game playing. In general game playing (GGP) the goal is to create game-playing systems that autonomously learn how to skillfully play a wide variety of games, given only the descriptions of the game rules. In this paper we review the history of the competition, discuss progress made so far, and list outstanding research challenges.

Participation will be open to active no later than Friday, June 19, 2013 finally, two years as immediate Past participants as well as other interested (5:00 PM local hotel time (PDT)).

One of our long term research goals is to develop systems to answer realistic questions (e.g., some mentioned in textbooks) about biological pathways that a biologist may ask. To answer such questions we need formalisms that can model pathways, simulate their execution, model intervention to those pathways, and compare simulations under different circumstances. We found Petri Nets to be the starting point of a suitable formalism for the modeling and simulation needs. However, we need to make extensions to the Petri Net model and also reason with multiple simulation runs and parallel state evolutions. Towards that end Answer Set Programming (ASP) implementation of Petri Nets would allow us to do both. In this paper we show how ASP can be used to encode basic Petri Nets in an intuitive manner. We then show how we can modify this encoding to model several Petri Net extensions by making small changes. We then highlight some of the reasoning capabilities that we will use to accomplish our ultimate research goal.

Machine Learning (ML) algorithms are used to train computers to perform a variety of complex tasks and improve with experience. Computers learn how to recognize patterns, make unintended decisions, or react to a dynamic environment. Certain trained machines may be more effective than others because they are based on more suitable ML algorithms or because they were trained through superior training sets. Although ML algorithms are known and publicly released, training sets may not be reasonably ascertainable and, indeed, may be guarded as trade secrets. While much research has been performed about the privacy of the elements of training sets, in this paper we focus our attention on ML classifiers and on the statistical information that can be unconsciously or maliciously revealed from them. We show that it is possible to infer unexpected but useful information from ML classifiers. In particular, we build a novel meta-classifier and train it to hack other classifiers, obtaining meaningful information about their training sets. This kind of information leakage can be exploited, for example, by a vendor to build more effective classifiers or to simply acquire trade secrets from a competitor's apparatus, potentially violating its intellectual property rights.

This manuscript provides optimization guarantees, generalization bounds, and statistical consistency results for AdaBoost variants which replace the exponential loss with the logistic and similar losses (specifically, twice differentiable convex losses which are Lipschitz and tend to zero on one side). The heart of the analysis is to show that, in lieu of explicit regularization and constraints, the structure of the problem is fairly rigidly controlled by the source distribution itself. The first control of this type is in the separable case, where a distribution-dependent relaxed weak learning rate induces speedy convergence with high probability over any sample. Otherwise, in the nonseparable case, the convex surrogate risk itself exhibits distribution-dependent levels of curvature, and consequently the algorithm's output has small norm with high probability.

Most real-world Planning problems are multi-objective, trying to minimize both the makespan of the solution plan, and some cost of the actions involved in the plan. But most, if not all existing approaches are based on single-objective planners, and use an aggregation of the objectives to remain in the single-objective context. Divide and Evolve (DaE) is an evolutionary planner that won the temporal deterministic satisficing track at the last International Planning Competitions (IPC). Like all Evolutionary Algorithms (EA), it can easily be turned into a Pareto-based Multi-Objective EA. It is however important to validate the resulting algorithm by comparing it with the aggregation approach: this is the goal of this paper. The comparative experiments on a recently proposed benchmark set that are reported here demonstrate the usefulness of going Pareto-based in AI Planning.

We develop stochastic variational inference, a scalable algorithm for approximating posterior distributions. We develop this technique for a large class of probabilistic models and we demonstrate it with two probabilistic topic models, latent Dirichlet allocation and the hierarchical Dirichlet process topic model. Using stochastic variational inference, we analyze several large collections of documents: 300K articles from Nature, 1.8M articles from The New York Times, and 3.8M articles from Wikipedia. Stochastic inference can easily handle data sets of this size and outperforms traditional variational inference, which can only handle a smaller subset. (We also show that the Bayesian nonparametric topic model outperforms its parametric counterpart.) Stochastic variational inference lets us apply complex Bayesian models to massive data sets.

Pattern-Based Constraint Satisfaction and Logic Puzzles develops a pure logic, pattern-based perspective of solving the finite Constraint Satisfaction Problem (CSP), with emphasis on finding the "simplest" solution. Different ways of reasoning with the constraints are formalised by various families of "resolution rules", each of them carrying its own notion of simplicity. A large part of the book illustrates the power of the approach by applying it to various popular logic puzzles. It provides a unified view of how to model and solve them, even though they involve very different types of constraints: obvious symmetric ones in Sudoku, non-symmetric but transitive ones (inequalities) in Futoshiki, topological and geometric ones in Map colouring, Numbrix and Hidato, and even much more complex non-binary arithmetic ones in Kakuro (or Cross Sums). It also shows that the most familiar techniques for these puzzles can indeed be understood as mere application-specific presentations of the general rules. Sudoku is used as the main example throughout the book, making it also an advanced level sequel to "The Hidden Logic of Sudoku" (another book by the same author), with: many examples of relationships among different rules and of exceptional situations; comparisons of the resolution potential of various families of rules; detailed statistics of puzzles hardness; analysis of extreme instances.

Introductory engineering courses within large universities often have annual enrollments which can reach up to a thousand students. It is very challenging to achieve differentiated instruction in classrooms with class sizes and student diversity of such great magnitude. Professors can only assess whether students have mastered a concept by using multiple choice questions, while detailed homework assignments, such as planar truss diagrams, are rarely assigned because professors and teaching assistants would be too overburdened with grading to return assignments with valuable feedback in a timely manner. In this paper, we introduce Mechanix, a sketch-based deployed tutoring system for engineering students enrolled in statics courses. Our system not only allows students to enter planar truss and free body diagrams into the system just as they would with pencil and paper, but our system checks the student's work against a hand-drawn answer entered by the instructor, and then returns immediate and detailed feedback to the student. Students are allowed to correct any errors in their work and resubmit until the entire content is correct and thus all of the objectives are learned. Since Mechanix facilitates the grading and feedback processes, instructors are now able to assign free response questions, increasing teacher's knowledge of student comprehension. Furthermore, the iterative correction process allows students to learn during a test, rather than simply displaying memorized information.

Game-based learning has been proven an effective method to engage students in the class. However, it is very challenging to balance playability and learnability when only developing digital games. Some "playable" games may not carry sufficient knowledge; some "learnable" games may reduce the students' interest and curiosity. In this ongoing research, we proposed an innovative learning method, "game-initiated learning." This method consists of three main steps: game, discussion and self-directedlearning. In this model, students can experience real-world problems from the game, discuss problems they found in the game, and finally, the instructors can deliver related knowledge that is useful to solving the problems previously discussed. To validate the proposed method, we selected a topic of disaster education in Taiwan and experimentally developed a set of course materials including a digital game, animation videos and an e-book. We conducted a review meeting, inviting experts from hydraulic engineering, game development, and disaster mediation as well as schoolteachers and students. The reviewers were asked to play the games and review all course materials. From the feedbacks of the reviewers, we found game-initiated learning an educational method with great potential in providing tacit and explicit knowledge about disaster management.