Humans possess an inherent ability to chunk sequences into their constituent parts. In fact, this ability is thought to bootstrap language skills to the learning of image patterns which might be a key to a more animal-like type of intelligence. Here, we propose a continual generalization of the chunking problem (an unsupervised problem), encompassing fixed and probabilistic chunks, discovery of temporal and causal structures and their continual variations. Additionally, we propose an algorithm called SyncMap that can learn and adapt to changes in the problem by creating a dynamic map which preserves the correlation between variables. Results of SyncMap suggest that the proposed algorithm learn near optimal solutions, despite the presence of many types of structures and their continual variation. When compared to Word2vec, PARSER and MRIL, SyncMap surpasses or ties with the best algorithm on $77\%$ of the scenarios while being the second best in the remaing $23\%$.

In this paper we propose a causal modeling approach to intersectional fairness, and a flexible, task-specific method for computing intersectionally fair rankings. Rankings are used in many contexts, ranging from Web search results to college admissions, but causal inference for fair rankings has received limited attention. Additionally, the growing literature on causal fairness has directed little attention to intersectionality. By bringing these issues together in a formal causal framework we make the application of intersectionality in fair machine learning explicit, connected to important real world effects and domain knowledge, and transparent about technical limitations. We experimentally evaluate our approach on real and synthetic datasets, exploring its behaviour under different structural assumptions.

A key challenge in satisfying planning is to use multiple heuristics within one heuristic search. An aggregation of multiple heuristic estimates, for example by taking the maximum, has the disadvantage that bad estimates of a single heuristic can negatively affect the whole search. Since the performance of a heuristic varies from instance to instance, approaches such as algorithm selection can be successfully applied. In addition, alternating between multiple heuristics during the search makes it possible to use all heuristics equally and improve performance. However, all these approaches ignore the internal search dynamics of a planning system, which can help to select the most helpful heuristics for the current expansion step. We show that dynamic algorithm configuration can be used for dynamic heuristic selection which takes into account the internal search dynamics of a planning system. Furthermore, we prove that this approach generalizes over existing approaches and that it can exponentially improve the performance of the heuristic search. To learn dynamic heuristic selection, we propose an approach based on reinforcement learning and show empirically that domain-wise learned policies, which take the internal search dynamics of a planning system into account, can exceed existing approaches in terms of coverage.

Decision and policy-makers in multi-criteria decision-making analysis take into account some strategies in order to analyze outcomes and to finally make an effective and more precise decision. Among those strategies, the modification of the normalization process in the multiple-criteria decision-making algorithm is still a question due to the confrontation of many normalization tools. Normalization is the basic action in defining and solving a MADM problem and a MADM model. Normalization is the first, also necessary, step in solving, i.e. the application of a MADM method. It is a fact that the selection of normalization methods has a direct effect on the results. One of the latest normalization methods introduced is the Logarithmic Normalization (LN) method. This new method has a distinguished advantage, reflecting in that a sum of the normalized values of criteria always equals 1. This normalization method had never been applied in any MADM methods before. This research study is focused on the analysis of the classical MADM methods based on logarithmic normalization. VIKOR and TOPSIS, as the two famous MADM methods, were selected for this reanalysis research study. Two numerical examples were checked in both methods, based on both the classical and the novel ways based on the LN. The results indicate that there are differences between the two approaches. Eventually, a sensitivity analysis is also designed to illustrate the reliability of the final results.

A latent bandit problem is one in which the learning agent knows the arm reward distributions conditioned on an unknown discrete latent state. The primary goal of the agent is to identify the latent state, after which it can act optimally. This setting is a natural midpoint between online and offline learning---complex models can be learned offline with the agent identifying latent state online---of practical relevance in, say, recommender systems. In this work, we propose general algorithms for this setting, based on both upper confidence bounds (UCBs) and Thompson sampling. Our methods are contextual and aware of model uncertainty and misspecification. We provide a unified theoretical analysis of our algorithms, which have lower regret than classic bandit policies when the number of latent states is smaller than actions. A comprehensive empirical study showcases the advantages of our approach.

In previous work, we developed a single Evolutionary Algorithm (EA) to solve random instances of the Anshel-Anshel-Goldfeld (AAG) key exchange protocol over polycyclic groups. The EA consisted of six simple heuristics which manipulated strings. The present work extends this by exploring the use of hyper-heuristics in group-theoretic cryptology for the first time. Hyper-heuristics are a way to generate new algorithms from existing algorithm components (in this case the simple heuristics), with the EAs being one example of the type of algorithm which can be generated by our hyper-heuristic framework. We take as a starting point the above EA and allow hyper-heuristics to build on it by making small tweaks to it. This adaptation is through a process of taking the EA and injecting chains of heuristics built from the simple heuristics. We demonstrate we can create novel heuristic chains, which when placed in the EA create algorithms which out-perform the existing EA. The new algorithms solve a markedly greater number of random AAG instances than the EA for harder instances. This suggests the approach could be applied to many of the same kinds of problems, providing a framework for the solution of cryptology problems over groups. The contribution of this paper is thus a framework to automatically build algorithms to attack cryptology problems.

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution shift. When the test task distribution is different from the training task distribution, the performance may degrade significantly. To address this issue, this paper proposes Model-based Adversarial Meta-Reinforcement Learning (AdMRL), where we aim to minimize the worst-case sub-optimality gap -- the difference between the optimal return and the return that the algorithm achieves after adaptation -- across all tasks in a family of tasks, with a model-based approach. We propose a minimax objective and optimize it by alternating between learning the dynamics model on a fixed task and finding the adversarial task for the current model -- the task for which the policy induced by the model is maximally suboptimal. Assuming the family of tasks is parameterized, we derive a formula for the gradient of the suboptimality with respect to the task parameters via the implicit function theorem, and show how the gradient estimator can be efficiently implemented by the conjugate gradient method and a novel use of the REINFORCE estimator. We evaluate our approach on several continuous control benchmarks and demonstrate its efficacy in the worst-case performance over all tasks, the generalization power to out-of-distribution tasks, and in training and test time sample efficiency, over existing state-of-the-art meta-RL algorithms.

We study the problem of sequential task assignment and collision-free routing for large teams of robots in applications with inter-task precedence constraints (e.g., task $A$ and task $B$ must both be completed before task $C$ may begin). Such problems commonly occur in assembly planning for robotic manufacturing applications, in which sub-assemblies must be completed before they can be combined to form the final product. We propose a hierarchical algorithm for computing makespan-optimal solutions to the problem. The algorithm is evaluated on a set of randomly generated problem instances where robots must transport objects between stations in a "factory "grid world environment. In addition, we demonstrate in high-fidelity simulation that the output of our algorithm can be used to generate collision-free trajectories for non-holonomic differential-drive robots.

We study the notion of boundedness in the context of positive existential rules, that is, whether there exists an upper bound to the depth of the chase procedure, that is independent from the initial instance. By focussing our attention on the oblivious and the semi-oblivious chase variants, we give a characterization of boundedness in terms of FO-rewritability and chase termination. We show that it is decidable to recognize if a set of rules is bounded for several classes and outline the complexity of the problem. This report contains the paper published at IJCAI 2019 and an appendix with full proofs.

Reputation is crucial to enabling human or software agents to select among alternative providers. Although several effective reputation assessment methods exist, they typically distil reputation into a numerical representation, with no accompanying explanation of the rationale behind the assessment. Such explanations would allow users or clients to make a richer assessment of providers, and tailor selection according to their preferences and current context. In this paper, we propose an approach to explain the rationale behind assessments from quantitative reputation models, by generating arguments that are combined to form explanations. Our approach adapts, extends and combines existing approaches for explaining decisions made using multi-attribute decision models in the context of reputation. We present example argument templates, and describe how to select their parameters using explanation algorithms. Our proposal was evaluated by means of a user study, which followed an existing protocol. Our results give evidence that although explanations present a subset of the information of trust scores, they are sufficient to equally evaluate providers recommended based on their trust score. Moreover, when explanation arguments reveal implicit model information, they are less persuasive than scores.