Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novel approximation scheme, namely the Kalman Temporal Differences (KTD) framework, that exhibits the following features: sample-efficiency, non-linear approximation, non-stationarity handling and uncertainty management. A first KTD-based algorithm is provided for deterministic Markov Decision Processes (MDP) which produces biased estimates in the case of stochastic transitions. Than the eXtended KTD framework (XKTD), solving stochastic MDP, is described. Convergence is analyzed for special cases for both deterministic and stochastic transitions. Related algorithms are experimented on classical benchmarks. They compare favorably to the state of the art while exhibiting the announced features.

The Gaussian process (GP) is a popular way to specify dependencies between random variables in a probabilistic model. In the Bayesian framework the covariance structure can be specified using unknown hyperparameters. Integrating over these hyperparameters considers different possible explanations for the data when making predictions. This integration is often performed using Markov chain Monte Carlo (MCMC) sampling. However, with non-Gaussian observations standard hyperparameter sampling approaches require careful tuning and may converge slowly. In this paper we present a slice sampling approach that requires little tuning while mixing well in both strong- and weak-data regimes.

Concept drift refers to a non stationary learning problem over time. The training and the application data often mismatch in real life problems. In this report we present a context of concept drift problem 1. We focus on the issues relevant to adaptive training set formation. We present the framework and terminology, and formulate a global picture of concept drift learners design. We start with formalizing the framework for the concept drifting data in Section 1. In Section 2 we discuss the adaptivity mechanisms of the concept drift learners. In Section 3 we overview the principle mechanisms of concept drift learners. In this chapter we give a general picture of the available algorithms and categorize them based on their properties. Section 5 discusses the related research fields and Section 5 groups and presents major concept drift applications. This report is intended to give a bird's view of concept drift research field, provide a context of the research and position it within broad spectrum of research fields and applications.

We have developed an efficient algorithm for the maximum likelihood joint tracking and association problem in a strong clutter for GMTI data. By using an iterative procedure of the dynamic logic process "from vague-to-crisp," the new tracker overcomes combinatorial complexity of tracking in highly-cluttered scenarios and results in a significant improvement in signal-to-clutter ratio.

Stochastic networks are a plausible representation of the relational information among entities in dynamic systems such as living cells or social communities. While there is a rich literature in estimating a static or temporally invariant network from observation data, little has been done toward estimating time-varying networks from time series of entity attributes. In this paper we present two new machine learning methods for estimating time-varying networks, which both build on a temporally smoothed $l_1$-regularized logistic regression formalism that can be cast as a standard convex-optimization problem and solved efficiently using generic solvers scalable to large networks. We report promising results on recovering simulated time-varying networks. For real data sets, we reverse engineer the latent sequence of temporally rewiring political networks between Senators from the US Senate voting records and the latent evolving regulatory networks underlying 588 genes across the life cycle of Drosophila melanogaster from the microarray time course.

We consider the problem of learning about and comparing the consequences of dynamic treatment strategies on the basis of observational data. We formulate this within a probabilistic decision-theoretic framework. Our approach is compared with related work by Robins and others: in particular, we show how Robins's 'G-computation' algorithm arises naturally from this decision-theoretic perspective. Careful attention is paid to the mathematical and substantive conditions required to justify the use of this formula. These conditions revolve around a property we term stability, which relates the probabilistic behaviours of observational and interventional regimes. We show how an assumption of 'sequential randomization' (or 'no unmeasured confounders'), or an alternative assumption of 'sequential irrelevance', can be used to infer stability. Probabilistic influence diagrams are used to simplify manipulations, and their power and limitations are discussed. We compare our approach with alternative formulations based on causal DAGs or potential response models. We aim to show that formulating the problem of assessing dynamic treatment strategies as a problem of decision analysis brings clarity, simplicity and generality.

Despite the recent progress towards efficient multiple kernel learning (MKL), the structured output case remains an open research front. Current approaches involve repeatedly solving a batch learning problem, which makes them inadequate for large scale scenarios. We propose a new family of online proximal algorithms for MKL (as well as for group-lasso and variants thereof), which overcomes that drawback. We show regret, convergence, and generalization bounds for the proposed method. Experiments on handwriting recognition and dependency parsing testify for the successfulness of the approach.

A method is presented for training an Input-Output Hidden Markov Model (IOHMM) to identify a player's current goal in an action-adventure game. The goals were Explore, Fight, or Return to Town, which served as the hidden states of the IOHMM. The observation model was trained by directing the player to achieve particular goals and counting actions. When trained on first-time players, training to the specific players did not appear to provide any benefits over a model trained to the experimenter. However, models trained on these players' subsequent trials were significantly better than the models trained to the specific players the first time, and also outperformed the model trained to the experimenter. This suggests that game goal recognition systems are best trained after the players have some time to develop a style of play. Systems for probabilistic reasoning over time could help game designers make games more responsive to players' individual styles and approaches.

Real-time pedestrian simulation for open-world games involves aggressive behavior simplification and culling to keep computational cost under control, but it is diffficult to predict whether these techniques will become unrealistic in certain situations. We propose a method of perceptually simulating highly realistic pedestrian behavior in virtual cities in realtime. Designers build a highly realistic simulation, from which a perceptually identical "perceptual simulation" is generated. Although the perceptual simulation simulates only a small portion of the world at a time, and does so with inexpensive approximations, it can be statistically guaranteed that the results are perceptually indistinguishable from those of the original simulation.

This paper proposes an automatic model-based approach that enables adaptive decision making in modern virtual games. It builds upon the Integrated MDP and POMDP Learning AgeNT (IMPLANT) architecture which has shown to provide plausible adaptive decision making in modern games. However, it suffers from highly time-consuming manual model specification problems. By incorporating an automated priority sweeping based model builder for the MDP, as well as using the Tactical Agent Personality for the POMDP, the work in this paper aims to resolve these problems. Empirical proof of concept is shown based on an implementation in a modern game scenario, whereby the enhanced IMPLANT agent is shown to exhibit superior adaptation performance over the old IMPLANT agent whilst eliminating manual model specifications and at the same time still maintaining plausible speeds.