In this article, we work towards the goal of developing agents that can learn to act in complex worlds. We develop a probabilistic, relational planning rule representation that compactly models noisy, nondeterministic action effects, and show how such rules can be effectively learned. Through experiments in simple planning domains and a 3D simulated blocks world with realistic physics, we demonstrate that this learning algorithm allows agents to effectively model world dynamics.

In real-life temporal scenarios, uncertainty and preferences are often essential and coexisting aspects. We present a formalism where quantitative temporal constraints with both preferences and uncertainty can be defined. We show how three classical notions of controllability (that is, strong, weak, and dynamic), which have been developed for uncertain temporal problems, can be generalized to handle preferences as well. After defining this general framework, we focus on problems where preferences follow the fuzzy approach, and with properties that assure tractability. For such problems, we propose algorithms to check the presence of the controllability properties. In particular, we show that in such a setting dealing simultaneously with preferences and uncertainty does not increase the complexity of controllability testing. We also develop a dynamic execution algorithm, of polynomial complexity, that produces temporal plans under uncertainty that are optimal with respect to fuzzy preferences.

In this paper, we show that there is a close relation between consistency in a constraint network and set intersection. A proof schema is provided as a generic way to obtain consistency properties from properties on set intersection. This approach not only simplifies the understanding of and unifies many existing consistency results, but also directs the study of consistency to that of set intersection properties in many situations, as demonstrated by the results on the convexity and tightness of constraints in this paper. Specifically, we identify a new class of tree convex constraints where local consistency ensures global consistency. This generalizes row convex constraints. Various consistency results are also obtained on constraint networks where only some, in contrast to all in the existing work,constraints are tight.

In Bayesian statistics, many problems can be expressed as the evaluation of the expectation of a quantity of interest with respect to the posterior distribution. Standard Monte Carlo method is often not applicable because the encountered posterior distributions cannot be sampled directly. In this case, the most popular strategies are the importance sampling method, Markov chain Monte Carlo, and annealing. In this paper, we introduce a new scheme for Bayesian inference, called Asymptotically Independent Markov Sampling (AIMS), which is based on the above methods. We derive important ergodic properties of AIMS. In particular, it is shown that, under certain conditions, the AIMS algorithm produces a uniformly ergodic Markov chain. The choice of the free parameters of the algorithm is discussed and recommendations are provided for this choice, both theoretically and heuristically based. The efficiency of AIMS is demonstrated with three numerical examples, which include both multi-modal and higher-dimensional target posterior distributions.

Authoring interactive stories where the player is afforded a wide range of social interactions results in a very large space of possible social and story situations. The amount of effort required to individually author for each of these circumstances can quickly become intractable. The social AI system Comme il Faut (CiF) aims to reduce the burden on the author by providing a playable model of social interaction where the author provides reusable and recombinable representations of social norms and social interactions. Motivated through examples from an in-development video game, Prom Week, this paper provides a detailed description of the structures with which CiF represents social knowledge and how this knowledge is employed to simulate social interactions between characters.

The task of keyhole (unobtrusive) plan recognition is central to adaptive game AI. “Tech trees” or “build trees” are the core of real-time strategy (RTS) game strategic (long term) planning. This paper presents a generic and simple Bayesian model for RTS build tree prediction from noisy observations, which parameters are learned from replays (game logs). This unsupervised machine learning approach involves minimal work for the game developers as it leverage players’ data (com- mon in RTS). We applied it to StarCraft1 and showed that it yields high quality and robust predictions, that can feed an adaptive AI.

This demo features a user interface for authoring stories and story fragments for use by the Minstrel Remixed story generation system. It also demonstrates Minstrel Remixed in use, allowing users to author story fragments and then have Minstrel Remixed expand these fragments and generate stories based on them. The focus is on the interface for story-fragment authoring, which exposes Minstrel's graph- of-frames knowledge representation format to the user in an interactive manner. It also exposes Minstrel Remixed's story generation capabilities as they exist currently, including the Author-Level Planning (ALP) and Transform Adapt Recall Methods (TRAM) systems.

Hiding and seeking is a cognitive ability frequently demonstrated by humans in both real life and video games. We use machine learning to automatically construct the first computational model of hide/seek behavior in adult humans in a video game like setting. The model is then run generatively in a novel environment and its behavior is found indistinguishable from actual human behavior by a panel of human judges.  In doing so the artificial intelligence agent using the model appears to have passed a version of the Turing test for hiding and seeking.

Characters are a critical part of storytelling and emotion is a vital part of character. Readers generally credit characters with human emotions, and it is these emotions which bring meaning to stories. To computationally construct interesting and meaningful stories we need a model of emotion which allows us to predict characters’ reactions to events in the world. There are many different psychological theories of emotion; the most popular to date for computational applications is the OCC theory. This paper describes a Discrete Event Calculus implementation of the OCC Theory of Emotion. To evaluate our system, we apply it to a selection of Aesop’s fables, and compare the output to the emotions readers expect in the same situations based on a survey.

Much of the most expressive behavior in humans - expressions of shock or alarm, gaze aversion, or explosive rage - are the result of automatic processes that engage before deliberative processing can respond. In some cases, such as weeping, the deliberative system may have only limited ability to override the automatic system. These processes are implemented by a network of phylogenetically old, special purpose, somewhat redundant systems that give rise to the particular idiosyncratic behavior we associate with automatic reactions to emotional events. In this paper, I'll review some of the ethological and neuropsychological results on low-level systems related to threat response, and their relation to the simulation of virtual characters. I will also discuss work in progress on building a medium-fidelity simulation of these systems.