Effective coordination is crucial to solve multi-agent collaborative (MAC) problems. While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize to scenarios different from those seen during training. In this paper, we consider MAC problems with some intrinsic notion of locality (e.g., geographic proximity) such that interactions between agents and tasks are locally limited. By leveraging this property, we introduce a novel structured prediction approach to assign agents to tasks. At each step, the assignment is obtained by solving a centralized optimization problem (the inference procedure) whose objective function is parameterized by a learned scoring model. We propose different combinations of inference procedures and scoring models able to represent coordination patterns of increasing complexity. The resulting assignment policy can be efficiently learned on small problem instances and readily reused in problems with more agents and tasks (i.e., zero-shot generalization). We report experimental results on a toy search and rescue problem and on several target selection scenarios in StarCraft: Brood War, in which our model significantly outperforms strong rule-based baselines on instances with 5 times more agents and tasks than those seen during training.

The Quadratic Assignment Problem (QAP) is a well-known permutation-based combinatorial optimization problem with real applications in industrial and logistics environments. Motivated by the challenge that this NPhard problem represents, it has captured the attention of the evolutionary computation community for decades. As a result, a large number of algorithms have been proposed to optimize this algorithm. Among these, exact methods are only able to solve instances of size n 40, and thus, many heuristic and metaheuristic methods have been applied to the QAP. In this work, we follow this direction by approaching the QAP through Estimation of Distribution Algorithms (EDAs). Particularly, a nonparametric distance-based exponential probabilistic model is used. Based on the analysis of the characteristics of the QAP, and previous work in the area, we introduce Kernels of Mallows Model under the Hamming distance to the context of EDAs. Conducted experiments point out that the performance of the proposed algorithm in the QAP is superior to (i) the classical EDAs adapted to deal with the QAP, and also (ii) to the specific EDAs proposed in the literature to deal with permutation problems.1. Introduction The Quadratic Assignment Problem (QAP) [30] is a well known combinatorial optimization problem. Along with other problems, such as the traveling salesman problem, the linear ordering problem and the flowshop scheduling problem, it belongs to the family of permutation-based (a permutation is a bijection of the set {1,...,n } onto itself) problems [10]. The QAP has been applied in many different environments over the years, to name but a few notable examples, selecting optimal hospital layouts [24], optimally placing components on circuit boards [44], assigning gates at airports [23] or optimizing data transmission [38]. Sahni and Gonzalez [45] proved that the QAP is an NPhard optimization problem, and as such, no polynomial-time exact algorithm can solve this problem unless P NP. M: The size of the set of selected solutions. S: The number of new solutions generated at each iteration.

We consider the task of causal structure learning over measurement dependence inducing latent (MeDIL) causal models. We show that this task can be framed in terms of the graph theoretical problem of finding edge clique covers, resulting in a simple algorithm for returning minimal MeDIL causal models (minMCMs). This algorithm is non-parametric, requiring no assumptions about linearity or Gaussianity. Furthermore, despite rather weak assumptions about the class of MeDIL causal models, we show that minimality in minMCMs implies three rather specific and interesting properties: first, minMCMs provide lower bounds on (i) the number of latent causal variables and (ii) the number of functional causal relations that are required to model a complex system at any level of granularity; second, a minMCM contains no causal links between the latent variables; and third, in contrast to factor analysis, a minMCM may require more latent than measurement variables.

A coreset (or core-set) of an input set is its small summation, such that solving a problem on the coreset as its input, provably yields the same result as solving the same problem on the original (full) set, for a given family of problems (models, classifiers, loss functions). Over the past decade, coreset construction algorithms have been suggested for many fundamental problems in e.g. machine/deep learning, computer vision, graphics, databases, and theoretical computer science. This introductory paper was written following requests from (usually non-expert, but also colleagues) regarding the many inconsistent coreset definitions, lack of available source code, the required deep theoretical background from different fields, and the dense papers that make it hard for beginners to apply coresets and develop new ones. The paper provides folklore, classic and simple results including step-by-step proofs and figures, for the simplest (accurate) coresets of very basic problems, such as: sum of vectors, minimum enclosing ball, SVD/ PCA and linear regression. Nevertheless, we did not find most of their constructions in the literature. Moreover, we expect that putting them together in a retrospective context would help the reader to grasp modern results that usually extend and generalize these fundamental observations. Experts might appreciate the unified notation and comparison table that links between existing results. Open source code with example scripts are provided for all the presented algorithms, to demonstrate their practical usage, and to support the readers who are more familiar with programming than math.

Endoscopic diagnosis is an important means for gastric polyp detection. In this paper, a panoramic image of gastroscopy is developed, which can display the inner surface of the stomach intuitively and comprehensively. Moreover, the proposed automatic detection solution can help doctors locate the polyps automatically, and reduce missed diagnosis. The main contributions of this paper are: firstly, a gastroscopic panorama reconstruction method is developed. The reconstruction does not require additional hardware devices, and can solve the problem of texture dislocation and illumination imbalance properly; secondly, an end-to-end multi-object detection for gastroscopic panorama is trained based on deep learning framework. Compared with traditional solutions, the automatic polyp detection system can locate all polyps in the inner wall of stomach in real time and assist doctors to find the lesions. Thirdly, the system was evaluated in the Affiliated Hospital of Zhejiang University. The results show that the average error of the panorama is less than 2 mm, the accuracy of the polyp detection is 95%, and the recall rate is 99%. In addition, the research roadmap of this paper has guiding significance for endoscopy-assisted detection of other human soft cavities.

Dynamic Multi-objective Optimization Problems (DMOPs) refer to optimization problems that objective functions will change with time. Solving DMOPs implies that the Pareto Optimal Set (POS) at different moments can be accurately found, and this is a very difficult job due to the dynamics of the optimization problems. The POS that have been obtained in the past can help us to find the POS of the next time more quickly and accurately. Therefore, in this paper we present a Support Vector Machine (SVM) based Dynamic Multi-Objective Evolutionary optimization Algorithm, called SVM-DMOEA. The algorithm uses the POS that has been obtained to train a SVM and then take the trained SVM to classify the solutions of the dynamic optimization problem at the next moment, and thus it is able to generate an initial population which consists of different individuals recognized by the trained SVM. The initial populuation can be fed into any population based optimization algorithm, e.g., the Nondominated Sorting Genetic Algorithm II (NSGA-II), to get the POS at that moment. The experimental results show the validity of our proposed approach.

Motivated by the recent advancements in deep Reinforcement Learning (RL), we develop an RL agent to manage the operation of storage devices in a household designed to maximize demand-side cost savings. The proposed technique is data-driven, and the RL agent learns from scratch on how to efficiently use the energy storage device under variable tariff-structures Contracting the concept of the "black box" where the techniques learned by the agent are ignored. We explain the learning progression of the RL agent, and the strategies it follows based on the capacity of the storage device.

Lucd, an Enterprise AI platform and solution services company, today announced it has partnered with AI Satellitez, whose mission is to provide artificial intelligence and machine learning models to businesses to optimize their operations. Lucd's Enterprise Artificial Intelligence platform provides digital transformation through the responsible use of data. Utilizing intellectual property combined with leading technologies and tools to form a complete open platform, Lucd enables all businesses to take advantage of the fast-moving AI market to gain a competitive advantage. "At Lucd, we are excited about our partnership with AI Satellitez as they provide best in class model creation capabilities that enhance the customer experience, driving business transformation with unique use cases for our customers," said John Leschorn, COO and Co-Founder at Lucd. "AI Satellitez is excited to partner with Lucd as they offer the best in class platform to run custom Machine Learning and Data Analytics models that we build for our clients. Their unique offer of a secure and compliant platform for our customers to store data and run models is a competitive advantage for us all," said Sam Reagin, VP of Sales for AI Satellitez.

Mercari is a marketplace app that makes it easy for people to safely sell and ship their things. Launched in 2013, the Mercari app has been downloaded over 100M times in Japan and the US. From fashion to toys, shoes to electronics and beyond, Mercari's mission is to create value in a global marketplace where anyone can buy and sell. Though we have over 1,800 employees, we still have a startup culture, where we encourage people to come up with big, crazy ideas, and to not be afraid of failure. Because the company is rapidly growing, you can set your own path, and there is enough transparency to allow our members to do so.

The director of sales at Pixellot, Charles Prichard, is convinced that there is a tendency that AI will automatically increase production to make sure that youth sports is cost-effective. An estimation of 45 million children and 6.5 million coaches is said to take part in different types of youth sports every year in the United States of America. However, many of the games are watched by these youngsters. Professional sports gain more access than local sports, and this is why a little boy of 14 will be so engrossed in his laptop at night trying to catch a game. These international sports have also gained more popularity.