Reinforcement Learning (RL) methods often rely on gradient estimates to learn an optimal policy for control problems. These expensive computations result in long training times, a poor rate of convergence, and sample inefficiency when applied to real-world problems with a large state and action space. Evolutionary Computation (EC)-based techniques offer a gradient-free apparatus to train a deep neural network for RL problems. In this work, we leverage the benefits of EC and propose a novel variant of genetic algorithm called SP-GA which utilizes a species-inspired weight initialization strategy and trains a population of deep neural networks, each estimating the Q-function for the RL problem. Efficient encoding of a neural network that utilizes less memory is also proposed which provides an intuitive mechanism to apply Gaussian mutations and single-point crossover. The results on Atari 2600 games outline comparable performance with gradient-based algorithms like Deep Q-Network (DQN), Asynchronous Advantage Actor Critic (A3C), and gradient-free algorithms like Evolution Strategy (ES) and simple Genetic Algorithm (GA) while requiring far fewer hyperparameters to train. The algorithm also improved certain Key Performance Indicators (KPIs) when applied to a Remote Electrical Tilt (RET) optimization task in the telecommunication domain.

The expert systems business has been through a terrible period in 1987–88. In the USA, the “Gang of Four”—the new venture software companies which once led the industry—have all run into losses and cut back staff more or less severely. Symbolics, whose high priced Lisp workstations have made it the biggest single company in artificial intelligence (AI), has hit an equally dramatic reversal of fortunes.

For the first time, post-conference workshops were organised for the International Conference on Deductive and Object-Oriented Databases (DOOD). There were two workshops focusing on knowledge discovery and temporal reasoning. This report is dedicated to one dealing with temporal reasoning.

Production systems have successfully made the transition from a trendy research idea to a routinely used programming paradigm. An important cause of this transition has been the several orders of magnitude speedup in program execution achieved in the past few years by the combination of better match algorithms, efficient compilation techniques and faster hardware platforms.

Reusing requirements improves product quality and the productivity of the development process. This paper investigates how the development of new requirements can be made more productive through reuse of the experience gained on similar requirements. This can be facilitated using a component-based reuse approach supported by a framework. Therefore, the central challenge for this research work is double: (1) to define a new concept for the requirement component as the combination of two types of knowledge: reusable knowledge and knowledge of reuse; (2) to define AFR (Analysis For Reuse) that represents the capitalization process by opposition to Analysis By Reuse that represents the process of reuse itself. Finally, we provide a case study related to the requirements of a hotel system to explain how the first process works. Through this approach, we use a framework ‘Requirements Repository Framework (R2F)’ in order to capitalize existing requirements within a repository for future reuse. We present the results of an experiment with three second-level student sections that used R2F in their IS240 course project; as well as with four student groups that used R2F in their respective senior projects. The objective of this experiment is to measure the usability of the proposed AFR process.

High utility itemsets mining (HUIM) is an important sub-field of frequent itemset mining (FIM). Recently, HUIM has received much attention in the field of data mining. High utility itemsets (HUIs) have proven to be quite useful in marketing, retail marketing, cross-marketing, and e-commerce. Traditional HUIM approaches suffer from a drawback as they need a user-defined minimum utility ($ min\_util $) threshold. It is not easy for the users to set the appropriate $ min\_util $ threshold to find actionable HUIs. To target this drawback, top-k HUIM has been introduced. top-k HUIM is more suitable for supermarket managers and retailers to prepare appropriate strategies to generate higher profit. In this paper, we provide an in-depth survey of the current status of top-k HUIM approaches. The paper presents the task of top-k HUIM and its relevant definitions. It reviews the top-k HUIM approaches and presents their advantages and disadvantages. The paper also discusses the important strategies of the top-k HUIM, their variations, and research opportunities. The paper provides a detailed summary, analysis, and future directions of the top-k HUIM field.

To this day, manipulation still stands as one of the hardest challenges in robotics. In this work, we examine the board game Dr. Eureka as a benchmark to encourage further development in the field. The game consists of a race to solve a manipulation puzzle: reordering colored balls in transparent tubes, in which the solution requires planning, dexterity and agility. In this work, we present a robot (Tactical Hazardous Operations Robot 3) that can solve this problem, nicely integrating several classical and state-of-the-art techniques. We represent the puzzle states as graph and solve it as a shortest path problem, in addition to applying computer vision combined with precise motions to perform the manipulation. In this paper, we also present a customized implementation of YOLO (called YOLO-Dr. Eureka) and we implement an original neural network (NN)-based incremental solution to the inverse kinematics problem. We show that this NN outperforms the inverse of the Jacobian method for large step sizes. Albeit requiring more computation per control cycle, the larger steps allow for much larger movements per cycle. To evaluate the experiment, we perform trials against a human using the same set of initial conditions.