This paper studies the statistical theory of offline reinforcement learning with deep ReLU networks. We consider the off-policy evaluation (OPE) problem where the goal is to estimate the expected discounted reward of a target policy given the logged data generated by unknown behaviour policies. We study a regression-based fitted Q evaluation (FQE) method using deep ReLU networks and characterize a finite-sample bound on the estimation error of this method under mild assumptions. The prior works in OPE with either general function approximation or deep ReLU networks ignore the data-dependent structure in the algorithm, dodging the technical bottleneck of OPE, while requiring a rather restricted regularity assumption. In this work, we overcome these limitations and provide a comprehensive analysis of OPE with deep ReLU networks. In particular, we precisely quantify how the distribution shift of the offline data, the dimension of the input space, and the regularity of the system control the OPE estimation error. Consequently, we provide insights into the interplay between offline reinforcement learning and deep learning.

Standard Neural Networks can learn mathematical operations, but they do not extrapolate. Extrapolation means that the model can apply to larger numbers, well beyond those observed during training. Recent architectures tackle arithmetic operations and can extrapolate; however, the equally important problem of quantitative reasoning remains unaddressed. In this work, we propose a novel architectural element, the Neural Status Register (NSR), for quantitative reasoning over numbers. Our NSR relaxes the discrete bit logic of physical status registers to continuous numbers and allows end-to-end learning with gradient descent. Experiments show that the NSR achieves solutions that extrapolate to numbers many orders of magnitude larger than those in the training set. We successfully train the NSR on number comparisons, piecewise discontinuous functions, counting in sequences, recurrently finding minimums, finding shortest paths in graphs, and comparing digits in images.

Reinforcement learning (RL) algorithms are typically limited to learning a single solution of a specified task, even though there often exists diverse solutions to a given task. Compared with learning a single solution, learning a set of diverse solutions is beneficial because diverse solutions enable robust few-shot adaptation and allow the user to select a preferred solution. Although previous studies have showed that diverse behaviors can be modeled with a policy conditioned on latent variables, an approach for modeling an infinite set of diverse solutions with continuous latent variables has not been investigated. In this study, we propose an RL method that can learn infinitely many solutions by training a policy conditioned on a continuous or discrete low-dimensional latent variable. Through continuous control tasks, we demonstrate that our method can learn diverse solutions in a data-efficient manner and that the solutions can be used for few-shot adaptation to solve unseen tasks.

In this paper we establish a link between preferential semantics for description logics and self-organising maps, which have been proposed as possible candidates to explain the psychological mechanisms underlying category generalisation. In particular, we show that a concept-wise multipreference semantics, which takes into account preferences with respect to different concepts and has been recently proposed for defeasible description logics, can be used to to provide a logical interpretation of SOMs. We also provide a logical interpretation of SOMs in terms of a fuzzy description logic as well as a probabilistic account.

Adapting an interface requires taking into account both the positive and negative effects that changes may have on the user. A carelessly picked adaptation may impose high costs to the user -- for example, due to surprise or relearning effort -- or "trap" the process to a suboptimal design immaturely. However, effects on users are hard to predict as they depend on factors that are latent and evolve over the course of interaction. We propose a novel approach for adaptive user interfaces that yields a conservative adaptation policy: It finds beneficial changes when there are such and avoids changes when there are none. Our model-based reinforcement learning method plans sequences of adaptations and consults predictive HCI models to estimate their effects. We present empirical and simulation results from the case of adaptive menus, showing that the method outperforms both a non-adaptive and a frequency-based policy.

Knowledge Graph Question Answering (KGQA) systems are based on machine learning algorithms, requiring thousands of question-answer pairs as training examples or natural language processing pipelines that need module fine-tuning. In this paper, we present a novel QA approach, dubbed TeBaQA. Our approach learns to answer questions based on graph isomorphisms from basic graph patterns of SPARQL queries. Learning basic graph patterns is efficient due to the small number of possible patterns. This novel paradigm reduces the amount of training data necessary to achieve state-of-the-art performance. TeBaQA also speeds up the domain adaption process by transforming the QA system development task into a much smaller and easier data compilation task. In our evaluation, TeBaQA achieves state-of-the-art performance on QALD-8 and delivers comparable results on QALD-9 and LC-QuAD v1. Additionally, we performed a fine-grained evaluation on complex queries that deal with aggregation and superlative questions as well as an ablation study, highlighting future research challenges.

In this work we discuss the incorporation of quadratic neurons into policy networks in the context of model-free actor-critic reinforcement learning. Quadratic neurons admit an explicit quadratic function approximation in contrast to conventional approaches where the the non-linearity is induced by the activation functions. We perform empiric experiments on several MuJoCo continuous control tasks and find that when quadratic neurons are added to MLP policy networks those outperform the baseline MLP whilst admitting a smaller number of parameters. The top returned reward is in average increased by $5.8\%$ while being about $21\%$ more sample efficient. Moreover, it can maintain its advantage against added action and observation noise.

Causal Learner is a toolbox for learning causal structure and Markov blanket (MB) from data. It integrates functions for generating simulated Bayesian network data, a set of state-of-the-art global causal structure learning algorithms, a set of state-of-the-art local causal structure learning algorithms, a set of state-of-the-art MB learning algorithms, and functions for evaluating algorithms. The data generation part of Causal Learner is written in R, and the rest of Causal Learner is written in MATLAB. Causal Learner aims to provide researchers and practitioners with an open-source platform for causal learning from data and for the development and evaluation of new causal learning algorithms. The Causal Learner project is available at http://bigdata.ahu.edu.cn/causal-learner.

Anyone still doubting whether fintech is disrupting Chicago's financial services industry only needs to look at a handful of recent partnerships to see that innovative technology is necessary for large enterprises to stay competitive in an ever-evolving market, lest they become obsolete. Take the following inked deals, for example. Amount -- a digital credit solution provider -- partnered with TD Bank and HSBC last year to help the two large institutions streamline their personal loan services, reflecting a marketplace that grew by $21 billion in 2018 to a record high of $138 billion, according to credit reporting agency TransUnion. Meanwhile, AI-powered financial compliance solution Ascent recently partnered with global information tech company IBM to help banks and other financial entities meet changing regulatory requirements. These types of partnerships help banks and financial institutions react to market changes and prepare for the future of finance; namely, by giving consumers more of the seamless user experiences they're used to and leveraging AI to streamline manual regulatory processes, saving valuable time and resources.

Machine learning technology is set to reduce herbicide use by up to 80 per cent, according to John Deere's Australia and New Zealand managing director Luke Chandler. Mr Chandler said this would be achieved by moving from a whole-of-field approach to a plant-by-plant management strategy. He said global agriculture was at an inflection point and technological developments would help drive productivity. Farmers across the world have been chasing economies of scale and the company's focus had been on building bigger, faster and stronger machinery to meet that growth, he said. "That's still important but as we shift towards this next frontier of agriculture, we really see machinery being driven by automation, easier to use, more precise types of technologies."