One scenario that commonly arises in computer games and military training simulations is predator-prey pursuit in which the goal of the non-player character agent is to successfully intercept a fleeing player. In this paper, we focus on a variant of the problem in which the agent does not have perfect information about the player’s location but has prior experience in combating the player. Effectively addressing this problem requires a combination of learning the opponent’s tactics while planning an interception strategy. Although for small maps, solving the problem with standard POMDP (Partially Observable Markov Decision Process) solvers is feasible, increasing the search area renders many standard techniques intractable due to the increase in the belief state size and required plan length. Here we introduce a new approach for solving the problem on large maps that exploits key events, high reward regions in the belief state discovered at the higher level of abstraction, to plan efficiently over the low-level map. We demonstrate that our hierarchical key-events planner can learn intercept policies from traces of previous pursuits significantly faster than a standard point-based POMDP solver, particularly as the maps scale in size.

Chatter bots are computer programs that can simulate a conversation through text chat. Current chatter bots perform well in artificial conversations consisting of pairs of utterance exchanges like a question-answer session where the context switches with every pair. But they perform poorly in longer conversations where the context is maintained across several utterance exchanges. Existing approaches to artificial conversation generation focus on linguistic and grammatical modeling to generate individual sentence-level utterances. We present a framework that enables longer and more meaningful conversations by combining concepts of content representation and conversation semantics. We also present a metric for evaluating the conversations based on Grice's maxims, that form the central idea in the theory of pragmatics.

There is an estimated 150 million children worldwide living with a disability. For many of these children in the U.S., physical therapy is provided as an intervention mechanism to support the child’s academic, developmental, and functional goals from birth and beyond. Typically, for a physical therapy intervention to be adopted, there must be sufficient evidence-based practices showing the efficacy of the given method in use with the target demographic. With the recent advances in robotics, therapeutic intervention protocols using robots is ideally positioned to make an impact in this domain. Unfortunately, there has not yet been sufficient evidence-based research focused on the use of robots in child-based therapy to result in a full systematic review of this area. As such, in this paper we provide a review of the emerging role of robotics in pediatric therapy, with the goal of summarizing the research that could possibly transition into providing evidence on the efficacy of robotic therapeutic interventions for children.

Abstracts of the invited talks presented at the 2013 FLAIRS conference. Talks include Robotics and Assistive Technologies: Their Emerging Role in Healthcare (Howard); Crossing the Data Science Chasm: The Perception of What Data Science Is and What It Needs to Be (Johnson); Who Are My Users and How I Can Help Them? The Quest of User-Adaptive Interaction (Conati); Neural Networks in Satellite-Based Atmospheric Remote Sensing (Chen); and The Use of Automated Reasoning for Software Verification of Microsoft Products (Bjorner).

Officers in 2013 of the Florida Ai Research Society

This volume contains the papers presented at the Twenty-Sixth International Florida Artificial Intelligence Research Society Conference (FLAIRS-26) held May 22–24, 2013, in St. Pete Beach, Florida, USA. The call for papers attracted 188 submissions, 74 to the general conference (including 25 poster abstracts) and 114 to the special tracks. Special tracks are a vital part of the FLAIRS conferences, with 9 held at FLAIRS-26.

We developed a new quantum annealing (QA) algorithm for Dirichlet process mixture (DPM) models based on the Chinese restaurant process (CRP). QA is a parallelized extension of simulated annealing (SA), i.e., it is a parallel stochastic optimization technique. Existing approaches [Kurihara et al. UAI2009, Sato et al. UAI2009] and cannot be applied to the CRP because their QA framework is formulated using a fixed number of mixture components. The proposed QA algorithm can handle an unfixed number of classes in mixture models. We applied QA to a DPM model for clustering vertices in a network where a CRP seating arrangement indicates a network partition. A multi core processor was used for running QA in experiments, the results of which show that QA is better than SA, Markov chain Monte Carlo inference, and beam search at finding a maximum a posteriori estimation of a seating arrangement in the CRP. Since our QA algorithm is as easy as to implement the SA algorithm, it is suitable for a wide range of applications.

Online portfolio selection is a fundamental problem in computational finance, which has been extensively studied across several research communities, including finance, statistics, artificial intelligence, machine learning, and data mining, etc. This article aims to provide a comprehensive survey and a structural understanding of published online portfolio selection techniques. From an online machine learning perspective, we first formulate online portfolio selection as a sequential decision problem, and then survey a variety of state-of-the-art approaches, which are grouped into several major categories, including benchmarks, "Follow-the-Winner" approaches, "Follow-the-Loser" approaches, "Pattern-Matching" based approaches, and "Meta-Learning Algorithms". In addition to the problem formulation and related algorithms, we also discuss the relationship of these algorithms with the Capital Growth theory in order to better understand the similarities and differences of their underlying trading ideas. This article aims to provide a timely and comprehensive survey for both machine learning and data mining researchers in academia and quantitative portfolio managers in the financial industry to help them understand the state-of-the-art and facilitate their research and practical applications. We also discuss some open issues and evaluate some emerging new trends for future research directions.

We study online learning under logarithmic loss with regular parametric models. Hedayati and Bartlett (2012b) showed that a Bayesian prediction strategy with Jeffreys prior and sequential normalized maximum likelihood (SNML) coincide and are optimal if and only if the latter is exchangeable, and if and only if the optimal strategy can be calculated without knowing the time horizon in advance. They put forward the question what families have exchangeable SNML strategies. This paper fully answers this open problem for one-dimensional exponential families. The exchangeability can happen only for three classes of natural exponential family distributions, namely the Gaussian, Gamma, and the Tweedie exponential family of order 3/2. Keywords: SNML Exchangeability, Exponential Family, Online Learning, Logarithmic Loss, Bayesian Strategy, Jeffreys Prior, Fisher Information1

Based on integrated infrastructure of resource sharing and computing in distributed environment, cloud computing involves the provision of dynamically scalable and provides virtualized resources as services over the Internet. These applications also bring a large scale heterogeneous and distributed information which pose a great challenge in terms of the semantic ambiguity. It is critical for application services in cloud computing environment to provide users intelligent service and precise information. Semantic information processing can help users deal with semantic ambiguity and information overload efficiently through appropriate semantic models and semantic information processing technology. The semantic information processing have been successfully employed in many fields such as the knowledge representation, natural language understanding, intelligent web search, etc. The purpose of this report is to give an overview of existing technologies for semantic information processing in cloud computing environment, to propose a research direction for addressing distributed semantic reasoning and parallel semantic computing by exploiting semantic information newly available in cloud computing environment.