Kernel-based reinforcement learning (KBRL) stands out among reinforcement learning algorithms for its strong theoretical guarantees. By casting the learning problem as a local kernel approximation, KBRL provides a way of computing a decision policy which is statistically consistent and converges to a unique solution. Unfortunately, the model constructed by KBRL grows with the number of sample transitions, resulting in a computational cost that precludes its application to large-scale or on-line domains. In this paper we introduce an algorithm that turns KBRL into a practical reinforcement learning tool. Kernel-based stochastic factorization (KBSF) builds on a simple idea: when a transition matrix is represented as the product of two stochastic matrices, one can swap the factors of the multiplication to obtain another transition matrix, potentially much smaller, which retains some fundamental properties of its precursor. KBSF exploits such an insight to compress the information contained in KBRL's model into an approximator of fixed size. This makes it possible to build an approximation that takes into account both the difficulty of the problem and the associated computational cost. KBSF's computational complexity is linear in the number of sample transitions, which is the best one can do without discarding data. Moreover, the algorithm's simple mechanics allow for a fully incremental implementation that makes the amount of memory used independent of the number of sample transitions. The result is a kernel-based reinforcement learning algorithm that can be applied to large-scale problems in both off-line and on-line regimes. We derive upper bounds for the distance between the value functions computed by KBRL and KBSF using the same data. We also illustrate the potential of our algorithm in an extensive empirical study in which KBSF is applied to difficult tasks based on real-world data.

Predictive state representations (PSRs) offer an expressive framework for modelling partially observable systems. By compactly representing systems as functions of observable quantities, the PSR learning approach avoids using local-minima prone expectation-maximization and instead employs a globally optimal moment-based algorithm. Moreover, since PSRs do not require a predetermined latent state structure as an input, they offer an attractive framework for model-based reinforcement learning when agents must plan without a priori access to a system model. Unfortunately, the expressiveness of PSRs comes with significant computational cost, and this cost is a major factor inhibiting the use of PSRs in applications. In order to alleviate this shortcoming, we introduce the notion of compressed PSRs (CPSRs). The CPSR learning approach combines recent advancements in dimensionality reduction, incremental matrix decomposition, and compressed sensing. We show how this approach provides a principled avenue for learning accurate approximations of PSRs, drastically reducing the computational costs associated with learning while also providing effective regularization. Going further, we propose a planning framework which exploits these learned models. And we show that this approach facilitates model-learning and planning in large complex partially observable domains, a task that is infeasible without the principled use of compression.

Conventional urban traffic control systems have been based on historical traffic data. Later advancements made use of detectors, which enabled the gathering of real time traffic data, in order to re organize and calibrate traffic signalization programs. Further evolvement provided the ability to forecast traffic conditions, in order to develop traffic signalization programs and strategies pre computed and applied at the most appropriate time frame for the optimal control of the current traffic conditions. We, propose the next generation of traffic control systems based on principles of Artificial Intelligence and Context Awareness. Most of the existing algorithms use average waiting time or length of the queue to assess an algorithm's performance. However, a low average waiting time may come at the cost of delaying other vehicles indefinitely. In our algorithm, besides the vehicle queue, we use'fairness' also as an important performance metric to assess an algorithm's performance.

Crowdsourcing has been proven to be an effective and efficient tool to annotate large datasets. User annotations are often noisy, so methods to combine the annotations to produce reliable estimates of the ground truth are necessary. We claim that considering the existence of clusters of users in this combination step can improve the performance. This is especially important in early stages of crowdsourcing implementations, where the number of annotations is low. At this stage there is not enough information to accurately estimate the bias introduced by each annotator separately, so we have to resort to models that consider the statistical links among them. In addition, finding these clusters is interesting in itself as knowing the behavior of the pool of annotators allows implementing efficient active learning strategies. Based on this, we propose in this paper two new fully unsupervised models based on a Chinese Restaurant Process (CRP) prior and a hierarchical structure that allows inferring these groups jointly with the ground truth and the properties of the users. Efficient inference algorithms based on Gibbs sampling with auxiliary variables are proposed. Finally, we perform experiments, both on synthetic and real databases, to show the advantages of our models over state-of-the-art algorithms.

A backbone of a propositional CNF formula is a variable whose truth value is the same in every truth assignment that satisfies the formula. The notion of backbones for CNF formulas has been studied in various contexts. In this paper, we introduce local variants of backbones, and study the computational complexity of detecting them. In particular, we consider k-backbones, which are backbones for sub-formulas consisting of at most k clauses, and iterative k-backbones, which are backbones that result after repeated instantiations of k-backbones. We determine the parameterized complexity of deciding whether a variable is a k-backbone or an iterative k-backbone for various restricted formula classes, including Horn, definite Horn, and Krom. We also present some first empirical results regarding backbones for CNF-Satisfiability (SAT). The empirical results we obtain show that a large fraction of the backbones of structured SAT instances are local, in contrast to random instances, which appear to have few local backbones.

Optimization problems arise in various disciplines such as engineering design, manufacturing system, economics etc. thus in view of the practical utility of optimization problems there is a need for efficient and robust computational algorithms which can solve optimization problems arising in different fields. Several NPhard combinatorial optimization problems, such as the traveling salesman problem, and yard management of container terminals can be modeled as QAPs.. Optimization is a process that finds a best, or optimal, solution for a problem. An optimization problem is defined as: Finding values of the variables that minimize or maximize the objective function while satisfying the constraints. The Optimization problems are centered on three factors: (1) an objective function which is to be minimized or maximized.

The psychological state of flow has been linked to optimizing human performance. A key condition of flow emergence is a match between the human abilities and complexity of the task. We propose a simple computational model of flow for Artificial Intelligence (AI) agents. The model factors the standard agent-environment state into a self-reflective set of the agent's abilities and a socially learned set of the environmental complexity. Maximizing the flow serves as a meta control for the agent. We show how to apply the meta-control policy to a broad class of AI control policies and illustrate our approach with a specific implementation. Results in a synthetic testbed are promising and open interesting directions for future work.

Sequential or online dimensional reduction is of interests due to the explosion of streaming data based applications and the requirement of adaptive statistical modeling, in many emerging fields, such as the modeling of energy end-use profile. Principal Component Analysis (PCA), is the classical way of dimensional reduction. However, traditional Singular Value Decomposition (SVD) based PCA fails to model data which largely deviates from Gaussian distribution. The Bregman Divergence was recently introduced to achieve a generalized PCA framework. If the random variable under dimensional reduction follows Bernoulli distribution, which occurs in many emerging fields, the generalized PCA is called Logistic PCA (LPCA). In this paper, we extend the batch LPCA to a sequential version (i.e. SLPCA), based on the sequential convex optimization theory. The convergence property of this algorithm is discussed compared to the batch version of LPCA (i.e. BLPCA), as well as its performance in reducing the dimension for multivariate binary-state systems. Its application in building energy end-use profile modeling is also investigated.

MinHash and SimHash are the two widely adopted Locality Sensitive Hashing (LSH) algorithms for large-scale data processing applications. Deciding which LSH to use for a particular problem at hand is an important question, which has no clear answer in the existing literature. In this study, we provide a theoretical answer (validated by experiments) that MinHash virtually always outperforms SimHash when the data are binary, as common in practice such as search. The collision probability of MinHash is a function of resemblance similarity ($\mathcal{R}$), while the collision probability of SimHash is a function of cosine similarity ($\mathcal{S}$). To provide a common basis for comparison, we evaluate retrieval results in terms of $\mathcal{S}$ for both MinHash and SimHash. This evaluation is valid as we can prove that MinHash is a valid LSH with respect to $\mathcal{S}$, by using a general inequality $\mathcal{S}^2\leq \mathcal{R}\leq \frac{\mathcal{S}}{2-\mathcal{S}}$. Our worst case analysis can show that MinHash significantly outperforms SimHash in high similarity region. Interestingly, our intensive experiments reveal that MinHash is also substantially better than SimHash even in datasets where most of the data points are not too similar to each other. This is partly because, in practical data, often $\mathcal{R}\geq \frac{\mathcal{S}}{z-\mathcal{S}}$ holds where $z$ is only slightly larger than 2 (e.g., $z\leq 2.1$). Our restricted worst case analysis by assuming $\frac{\mathcal{S}}{z-\mathcal{S}}\leq \mathcal{R}\leq \frac{\mathcal{S}}{2-\mathcal{S}}$ shows that MinHash indeed significantly outperforms SimHash even in low similarity region. We believe the results in this paper will provide valuable guidelines for search in practice, especially when the data are sparse.

Distributed computing offers a high degree of flexibility to accommodate modern learning constraints and the ever increasing size of datasets involved in massive data issues. Drawing inspiration from the theory of distributed computation models developed in the context of gradient-type optimization algorithms, we present a consensus-based asynchronous distributed approach for nonparametric online regression and analyze some of its asymptotic properties. Substantial numerical evidence involving up to 28 parallel processors is provided on synthetic datasets to assess the excellent performance of our method, both in terms of computation time and prediction accuracy.