Procedural content generation (PCG) for videogames relies on a commitment to the semantics of the game. Concepts such as enemies or solidity are required for the creation of levels for platformer games. As humans, we can instantly identify the underlying semantics of a game from brief snippets of game play video or from playing the game. Previous PCG systems have needed humans to identify the semantic properties of objects in the game, either implicitly or explicitly. We propose a system that can automatically learn the semantic properties of game objects by observation of events in the game via a causal learning framework. We apply this learning approach to play traces from the Super Mario Bros. series.

When machine learning algorithms are used in life-critical or mission-critical applications (e.g., self driving cars, cyber security, surgical robotics), it is important to ensure that they provide some high-level correctness guarantees. We introduce a paradigm called Trusted Machine Learning (TML) with the goal of making learning techniques more trustworthy. We outline methods that show how symbolic analysis (specifi- cally parametric model checking) can be used to learn the dynamical model of a system where the learned model satis- fies correctness requirements specified in the form of temporal logic properties (e.g., safety, liveness). When a learned model does not satisfy the desired guarantees, we try two approaches: (1) Model Repair, wherein we modify a learned model directly, and (2) Data Repair, wherein we modify the data so that re-learning from the modified data will result in a trusted model. Model Repair tries to make the minimal changes to the trained model while satisfying the properties, whereas Data Repair tries to make the minimal changes to the dataset used to train the model for ensuring satisfaction of the properties. We show how the Model Repair and Data Repair problems can be solved for the case of probabilistic models, specifically Discrete-Time Markov Chains (DTMC) or Markov Decision Processes (MDP), when the desired properties are expressed in Probabilistic Computation Tree Logic (PCTL). Specifically, we outline how the parameter learning problem in the probabilistic Markov models under temporal logic constraints can be equivalently expressed as a non-linear optimization with non-linear rational constraints, by performing symbolic transformations using a parametric model checker. We illustrate the approach on two case studies: a controller for automobile lane changing, and query router for a wireless sensor network.

The purpose of this paper is to show the expressiveness of two different formalisms that combine logic and probabilistic reasoning: Stochastic Logic Programs (SLPs) and Probabilistic Concurrent Constraint Programs (PCCs). We analyse the relation between the two and we show that we are able to express, using PCC programs, some of the main probabilistic graphical models: Bayesian Networks, Markov random fields, Markov chains, Hidden Markov models, Stochastic Context Free Grammars and Markov Logic Networks. We express this last framework also in SLPs.

Weighted model counting (WMC) has recently emerged as an effective and general approach to probabilistic inference, offering a computational framework for encoding a variety of formalisms, such as factor graphs and Bayesian networks.The advent of large-scale probabilistic knowledge bases has generated further interest in relational probabilistic representations, obtained by according weights to first-order formulas, whose semantics is given in terms of the ground theory, and solved by WMC. A fundamental limitation is that the domain of quantification, by construction and design, is assumed to be finite, which is at odds with areas such as vision and language understanding, where the existence of objects must be inferred from raw data. Dropping the finite-domain assumption has been known to improve the expressiveness of a first-order language for open-universe purposes, but these languages, so far, have eluded WMC approaches. In this paper, we revisit relational probabilistic models over an infinite domain, and establish a number of results that permit effective algorithms. We demonstrate this language on a number of examples, including a parameterized version of Pearl's Burglary-Earthquake-Alarm Bayesian network.

Player goal recognition in digital games offers the promise of enabling games to dynamically customize player experience. Goal recognition aims to recognize players’ high-level intentions using a computational model trained on a player behavior corpus. A significant challenge is posed by devising reliable goal recognition models with a behavior corpus characterized by highly idiosyncratic player actions. In this paper, we introduce deep LSTM-based goal recognition models that handle the inherent uncertainty stemming from noisy, non-optimal player behaviors. Empirical evaluation indicates that deep LSTMs outperform competitive baselines including single-layer LSTMs, n-gram encoded feedforward neural networks, and Markov logic networks for a goal recognition corpus collected from an open-world educational game. In addition to metric-based goal recognition model evaluation, we investigate a visualization technique to show a dynamic goal recognition model’s performance over the course of a player’s goal-seeking behavior. Deep LSTMs, which are capable of both sequentially and hierarchically extracting salient features of player behaviors, show significant promise as a goal recognition approach for open-world digital games.

Prior work on viewing plan recognition as parsing of grammars has assumed completely observable actions. This paper provides an algorithm to rewrite plan grammars to allow for recognizing partially observable actions.  For the ELEXIR (Geib 2009) system, the impact of this rewriting on plan recognition runtime is shown to be limited to those plans that actually use the partially observable actions.

Context-recognition and activity recognition systems in multi-user environments such as smart homes, usually assume to know the number of occupants in the environment. However, being able to count the number of users in the environment is important in order to accurately recognize the activities of (groups of) agents. For smart environments without cameras, the problem of counting the number of agents is non-trivial. This is in part due to the difficulty of using a single non-vision based sensors to discriminate between one or several persons, and thus information from several sensors must be combined in order to reason about the presence of several agents. In this paper we address the problem of counting the number of agents in a topologically known environment using simple sensors that can indicate anonymous human presence. To do so, we connect an ontology to a probabilistic model (a Hidden Markov Model) in order to estimate the number of agents in each section of the environment. We evaluate our methods on a smart home setup where a number of motion and pressure sensors are distributed in various rooms of the home.

This work addresses the problem of choosing an appropriate plan for achieving a goal in any realistic complex situation where an agent has to respond and act upon uncertain and/or an unknown information. We use the belief-desire-intention (BDI) model, a popular model for developing agents. The flexibility of choosing among different plans to achieve a desired goal is one of the benefits of this model. This paper describes a particular algorithm for selecting the most appropriate plan. Since the agent may have to reason with incomplete or uncertain information, we explore how to integrate probabilities in the agent model for taking an appropriate action and keeping the system behavior within acceptable boundaries and compliance to acceptable norms. Considering the uncertainty of the current state of the environment, this process relies on probability and utility theory. The plan selection algorithm has been implemented with Jadex

Within population health information systems, indicators are commonly presented as independent, cross-sectional measures, neglecting the multivariate, longitudinal nature of disease progression and health care use. We use administrative claims data for patients with a previous diagnosis of chronic obstructive pulmonary disease in Montreal, Canada to explore two approaches to facilitating the discovery and interpretation of patterns across indicators and over time. The first approach identifies regional clusters based on patterns across four health service indicators. Our second approach uses a hidden Markov model to analyze individuallevel trajectories based on the same four indicators. Both approaches offer additional insights, such as a dual interpretation of low use of general practitioner services. These approaches to the analysis and visualization of health indicators can provide a foundation for information displays that will help decision makers identify areas of concern, predict future disease burden, and implement appropriate policies.

For a multitude of tasks that come naturally to humans, performance of AI systems is inferior to human level performance. We show how human intellect made available via crowdsourcing can be used to complement an existing system during execution. We introduce a hybrid workflow that queries people to verify and correct the output of the system and present a simulation-based workflow optimization method to balance the cost of human input with the expected improvement in performance. Through empirical evaluations on an image captioning system, we show that the hybrid system, which combines the AI system with human input, significantly outperforms the automated system by properly trading off the cost of human input with expected benefit. Finally, we show that human input collected at execution time can be used to teach the system about its errors and limitations.