The actor and the critic are approximated by Normalized Gaussian Networks (NGnet), which are networks of local linear regression units. The NGnet is trained by the online EM algorithm proposed in our previous paper.We apply our RL method to the task of swinging-up and stabilizing a single pendulum and the task of balancing a double pendulumnear the upright position. The experimental results show that our RL method can be applied to optimal control problems havingcontinuous state/action spaces and that the method achieves good control with a small number of trial-and-errors. 1 INTRODUCTION Reinforcement learning (RL) methods (Barto et al., 1990) have been successfully applied to various Markov decision problems having finite state/action spaces, such as the backgammon game (Tesauro, 1992) and a complex task in a dynamic environment (Lin,1992). On the other hand, applications to continuous state/action problems (Werbos, 1990; Doya, 1996; Sofge & White, 1992) are much more difficult than the finite state/action cases. Good function approximation methods and fast learning algorithms are crucial for successful applications.

Dyadzc data refers to a domain with two finite sets of objects in which observations are made for dyads, i.e., pairs with one element from either set. This type of data arises naturally in many application rangingfrom computational linguistics and information retrieval to preference analysis and computer vision. In this paper, we present a systematic, domain-independent framework of learning fromdyadic data by statistical mixture models. Our approach covers different models with fiat and hierarchical latent class structures. Wepropose an annealed version of the standard EM algorithm for model fitting which is empirically evaluated on a variety of data sets from different domains. 1 Introduction Over the past decade learning from data has become a highly active field of research distributedover many disciplines like pattern recognition, neural computation, statistics,machine learning, and data mining.

The technique of principal component analysis (PCA) has recently been expressed as the maximum likelihood solution for a generative latent variable model. In this paper we use this probabilistic reformulation as the basis for a Bayesian treatment of PCA. Our key result is that effective dimensionalityof the latent space (equivalent to the number of retained principal components) can be determined automatically as part of the Bayesian inference procedure. An important application of this framework is to mixtures of probabilistic PCA models, in which each component can determine its own effective complexity. 1 Introduction Principal component analysis (PCA) is a widely used technique for data analysis. Recently Tipping and Bishop (1997b) showed that a specific form of generative latent variable model has the property that its maximum likelihood solution extracts the principal subspace of the observed data set.

Dirichlet distribution (see for instance [4]).

Sparse coding is a method for finding a representation of data in which each of the components of the representation is only rarely significantly active. Such a representation is closely related to redundancy reductionand independent component analysis, and has some neurophysiological plausibility. In this paper, we show how sparse coding can be used for denoising. Using maximum likelihood estimation of nongaussian variables corrupted by gaussian noise, we show how to apply a shrinkage nonlinearity on the components of sparse coding so as to reduce noise. Furthermore, we show how to choose the optimal sparse coding basis for denoising.

The Association for the Advancement of Artificial Intelligence (AAAI) held its 1998 Fall Symposium Series on 23 to 25 October at the Omni Rosen Hotel in Orlando, Florida. This article contains summaries of seven of the symposia that were conducted: (1) Cognitive Robotics; (2) Distributed, Continual Planning; (3) Emotional and Intelligent: The Tangled Knot of Cognition; (4) Integrated Planning for Autonomous Agent Architectures; (5) Planning with Partially Observable Markov Decision Processes; (6) Reasoning with Visual and Diagrammatic Representations; and (7) Robotics and Biology: Developing Connections.

AI has embraced medical applications from its inception, and some of the earliest work in successful application of AI technology occurred in medical contexts. Medicine in the twenty-first century will be very different than medicine in the late twentieth century. Fortunately, the technical challenges to AI that emerge are similar, and the prospects for success are high.

A Bayesian network is a compact, expressive representation of uncertain relationships among parameters in a domain. In this article, I introduce basic methods for computing with Bayesian networks, starting with the simple idea of summing the probabilities of events of interest. The article introduces major current methods for exact computation, briefly surveys approximation methods, and closes with a brief discussion of open issues.

The last few years have seen a surge in interest in the use of techniques from Bayesian decision theory to address problems in AI. Decision theory provides a normative framework for representing and reasoning about decision problems under uncertainty. The articles cover the topics of inference in Bayesian networks, decision-theoretic planning, and qualitative decision theory. Here, I provide a brief introduction to Bayesian networks and then cover applications of Bayesian problem-solving techniques, knowledge-based model construction and structured representations, and the learning of graphic probability models.

The recent advances in computer speed and algorithms for probabilistic inference have led to a resurgence of work on planning under uncertainty. The aim is to design AI planners for environments where there might be incomplete or faulty information, where actions might not always have the same results, and where there might be trade-offs between the different possible outcomes of a plan. Addressing uncertainty in AI, planning algorithms will greatly increase the range of potential applications, but there is plenty of work to be done before we see practical decision-theoretic planning systems. This article outlines some of the challenges that need to be overcome and surveys some of the recent work in the area.