Distributed online optimization and game have been increasingly researched in the last decade, mostly motivated by its wide applications in sensor networks, robotics (e.g., distributed target tracking and formation control), smart grids, deep learning, and so forth. In these problems, there is a network of agents who may be cooperative (i.e., distributed online optimization) or noncooperative (i.e., online game) through local information exchanges. And the local cost function of each agent is often time-varying in dynamic and even adversarial environments. At each time, a decision must be made by each agent based on historical information at hand without knowing future information on cost functions. For these problems, a comprehensive survey is still lacking. This paper aims to provide a thorough overview of distributed online optimization and game from the perspective of problem settings, communication, computation, algorithms, and performances. In addition, some potential future directions are also discussed.

Companies struggle to continuously develop and deploy AI models to complex production systems due to AI characteristics while assuring quality. To ease the development process, continuous pipelines for AI have become an active research area where consolidated and in-depth analysis regarding the terminology, triggers, tasks, and challenges is required. This paper includes a Multivocal Literature Review where we consolidated 151 relevant formal and informal sources. In addition, nine-semi structured interviews with participants from academia and industry verified and extended the obtained information. Based on these sources, this paper provides and compares terminologies for DevOps and CI/CD for AI, MLOps, (end-to-end) lifecycle management, and CD4ML. Furthermore, the paper provides an aggregated list of potential triggers for reiterating the pipeline, such as alert systems or schedules. In addition, this work uses a taxonomy creation strategy to present a consolidated pipeline comprising tasks regarding the continuous development of AI. This pipeline consists of four stages: Data Handling, Model Learning, Software Development and System Operations. Moreover, we map challenges regarding pipeline implementation, adaption, and usage for the continuous development of AI to these four stages.

The almost unfathomable scale of the energy transition required for rapid decarbonization: in the energy sector alone, reaching net-zero greenhouse gas emissions will require infrastructure investments costing between $92 trillion and $173 trillion of by 2050, according to estimates by BloombergNEF. AI has a massive role to play here, as "even small gains in flexibility, efficiency or capacity in clean energy and low-carbon industry can therefore lead to trillions in value and savings."

CGG (www.cgg.com) is a global technology and HPC leader that provides data, products, services and solutions in Earth science, data science, sensing and monitoring. Our unique portfolio supports our clients in efficiently and responsibly solving complex digital, energy transition, natural resource, environmental, and infrastructure challenges for a more sustainable future. We are looking for experienced and talented individuals to join our team! As a Machine Learning engineer, you'll play a vital role in the continual development of our geoscience analytic techniques. You will work closely with researchers, the software development group and the scientists in our geoscience teams to implement machine learning and deep learning solutions.

Recent developments in artificial intelligence and automation support a new drug design paradigm: autonomous drug design. Under this paradigm, generative models can provide suggestions on thousands of molecules with specific properties, and automated laboratories can potentially make, test and analyze molecules with minimal human supervision. However, since still only a limited number of molecules can be synthesized and tested, an obvious challenge is how to efficiently select among provided suggestions in a closed-loop system. We formulate this task as a stochastic multi-armed bandit problem with multiple plays, volatile arms and similarity information. To solve this task, we adapt previous work on multi-armed bandits to this setting, and compare our solution with random sampling, greedy selection and decaying-epsilon-greedy selection strategies. According to our simulation results, our approach has the potential to perform better exploration and exploitation of the chemical space for autonomous drug design.

With the increasing availability of data for Prognostics and Health Management (PHM), Deep Learning (DL) techniques are now the subject of considerable attention for this application, often achieving more accurate Remaining Useful Life (RUL) predictions. However, one of the major challenges for DL techniques resides in the difficulty of obtaining large amounts of labelled data on industrial systems. To overcome this lack of labelled data, an emerging learning technique is considered in our work: Self-Supervised Learning, a sub-category of unsupervised learning approaches. This paper aims to investigate whether pre-training DL models in a self-supervised way on unlabelled sensors data can be useful for RUL estimation with only Few-Shots Learning, i.e. with scarce labelled data. In this research, a fatigue damage prognostics problem is addressed, through the estimation of the RUL of aluminum alloy panels (typical of aerospace structures) subject to fatigue cracks from strain gauge data. Synthetic datasets composed of strain data are used allowing to extensively investigate the influence of the dataset size on the predictive performance. Results show that the self-supervised pre-trained models are able to significantly outperform the non-pre-trained models in downstream RUL prediction task, and with less computational expense, showing promising results in prognostic tasks when only limited labelled data is available.

Efficient exploration strategies are vital in tasks such as search-and-rescue missions and disaster surveying. Unmanned Aerial Vehicles (UAVs) have become particularly popular in such applications, promising to cover large areas at high speeds. Moreover, with the increasing maturity of onboard UAV perception, research focus has been shifting toward higher-level reasoning for single- and multi-robot missions. However, autonomous navigation and exploration of previously unknown large spaces still constitutes an open challenge, especially when the environment is cluttered and exhibits large and frequent occlusions due to high obstacle density, as is the case of forests. Moreover, the problem of long-distance wireless communication in such scenes can become a limiting factor, especially when automating the navigation of a UAV swarm. In this spirit, this work proposes an exploration strategy that enables UAVs, both individually and in small swarms, to quickly explore complex scenes in a decentralized fashion. By providing the decision-making capabilities to each UAV to switch between different execution modes, the proposed strategy strikes a great balance between cautious exploration of yet completely unknown regions and more aggressive exploration of smaller areas of unknown space. This results in full coverage of forest areas of variable density, consistently faster than the state of the art. Demonstrating successful deployment with a single UAV as well as a swarm of up to three UAVs, this work sets out the basic principles for multi-root exploration of cluttered scenes, with up to 65% speed up in the single UAV case and 40% increase in explored area for the same mission time in multi-UAV setups.

Developing Hybrid Machine Learning Models to Assign Health Score to Railcar Fleets for Optimal Decision Making Mahyar Ejlali, Ebrahim Arian, Sajjad Taghiyeh, Kristina Chambers, Amir Hossein Sadeghi, Demet Cakdi, Robert B Handfield An expert hybrid predictive fault method is proposed based on fast-DBSCAN and PCA. Inspection data from 1986-2020 of North American Railcar Owner (NARO) is used. The model is able to predict future faults in the railcar fleet accurately. Abstract A large amount of data is generated during the operation of a railcar fleet, which can easily lead to dimensional disaster and reduce the resiliency of the railcar network. To solve these issues and offer predictive maintenance, this research introduces a hybrid fault diagnosis expert system method that combines density-based spatial clustering of applications with noise (DBSCAN) and principal component analysis (PCA). Firstly, the DBSCAN method is used to cluster categorical data that are similar to one another within the same group. Secondly, PCA algorithm is applied to reduce the dimensionality of the data and eliminate redundancy in order to improve the accuracy of fault diagnosis. Finally, we explain the engineered features and evaluate the selected models by using the Gain Chart and Area Under Curve (AUC) metrics. We use the hybrid expert system model to enhance maintenance planning decisions by assigning a health score to the railcar system of the North American Railcar Owner (NARO). According to the experimental results, our expert model can detect 96.4% of failures within 50% of the sample. This suggests that our method is effective at diagnosing failures in railcars fleet. Keywords: Expert system, Predictive maintenance, Railcar maintenance, Machine learning, Maintenance health score 1. Introduction Maintenance consists of activities that ensure the railcar assets continue to operate safely and reliably. These activities include inspection, repair, testing, and replacement of parts.

In this paper, we investigate Nash-regret minimization in congestion games, a class of games with benign theoretical structure and broad real-world applications. We first propose a centralized algorithm based on the optimism in the face of uncertainty principle for congestion games with (semi-)bandit feedback, and obtain finite-sample guarantees. Then we propose a decentralized algorithm via a novel combination of the Frank-Wolfe method and G-optimal design. By exploiting the structure of the congestion game, we show the sample complexity of both algorithms depends only polynomially on the number of players and the number of facilities, but not the size of the action set, which can be exponentially large in terms of the number of facilities. We further define a new problem class, Markov congestion games, which allows us to model the non-stationarity in congestion games. We propose a centralized algorithm for Markov congestion games, whose sample complexity again has only polynomial dependence on all relevant problem parameters, but not the size of the action set.

The aim of this work is to utilize an adaptive decentralized control method called virtual decomposition control (VDC) to control the orientation and position of the end-effector of a 7 degrees of freedom (DoF) right-hand upper-limb exoskeleton. The prevailing adaptive VDC approach requires tuning of 13n adaptation gains along with 26n upper and lower parameter bounds, where n is the number of rigid bodies. Therefore, utilizing the VDC scheme to control high DoF robots like the 7-DoF upper-limb exoskeleton can be an arduous task. In this paper, a new adaptation function, so-called natural adaptation law (NAL), is employed to eliminate these burdens from VDC, which results in reducing all 13n gains to one and removing dependency on upper and lower bounds. In doing so, VDC-based dynamic equations are restructured, and inertial parameter vectors are made compatible with NAL. Then, the NAL adaptation function is exploited to design a new adaptive VDC scheme. This novel adaptive VDC approach ensures physical consistency conditions for estimated parameters with no need for upper and lower bounds. Finally, the asymptotic stability of the algorithm is proved with the virtual stability concept and the accompanying function. The experimental results are utilized to demonstrate the excellent performance of the proposed new adaptive VDC scheme.