With the impact of real-time processing being realized in the recent past, the need for efficient implementations of reinforcement learning algorithms has been on the rise. Albeit the numerous advantages of Bellman equations utilized in RL algorithms, they are not without the large search space of design parameters. This research aims to shed light on the design space exploration associated with reinforcement learning parameters, specifically that of Policy Iteration. Given the large computational expenses of fine-tuning the parameters of reinforcement learning algorithms, we propose an auto-tuner-based ordinal regression approach to accelerate the process of exploring these parameters and, in return, accelerate convergence towards an optimal policy. Our approach provides 1.82x peak speedup with an average of 1.48x speedup over the previous state-of-the-art.

With the rapid surge in the number of on-road Electric Vehicles (EVs), the amount of spent lithium-ion (Li-ion) batteries is also expected to explosively grow. The spent battery packs contain valuable metal and materials that should be recovered, recycled, and reused. However, only less than 5% of the Li-ion batteries are currently recycled, due to a multitude of challenges in technology, logistics and regulation. Existing battery recycling is performed manually, which can pose a series of risks to the human operator as a consequence of remaining high voltage and chemical hazards. Therefore, there is a critical need to develop an automated battery recycling system. In this paper, we present ABatRe-sim, an open-source robotic battery recycling simulator, to facilitate the research and development in efficient and effective battery recycling au-omation. Specifically, we develop a detailed CAD model of the battery pack (with screws, wires, and battery modules), which is imported into Gazebo to enable robot-object interaction in the robot operating system (ROS) environment. It also allows the simulation of battery packs of various aging conditions. Furthermore, perception, planning, and control algorithms are developed to establish the benchmark to demonstrate the interface and realize the basic functionalities for further user customization. Discussions on the utilization and future extensions of the simulator are also presented.

Deep learning (DL) algorithms have been widely applied to short-term voltage stability (STVS) assessment in power systems. However, transferring the knowledge learned in one power grid to other power grids with topology changes is still a challenging task. This paper proposed a transferable DL-based model for STVS assessment by constructing the topology-aware voltage dynamic features from raw PMU data. Since the reactive power flow and grid topology are essential to voltage stability, the topology-aware and physics-informed voltage dynamic features are utilized to effectively represent the topological and temporal patterns from post-disturbance system dynamic trajectories. The proposed DL-based STVS assessment model is tested under random operating conditions on the New England 39-bus system. It has 99.99\% classification accuracy of the short-term voltage stability status using the topology-aware and physics-informed voltage dynamic features. In addition to high accuracy, the experiments show good adaptability to PMU errors. Moreover, The proposed STVS assessment method has outstanding performance on new grid topologies after fine-tuning. In particular, the highest accuracy reaches 99.68\% in evaluation, which demonstrates a good knowledge transfer ability of the proposed model for power grid topology change.

The prospect of informed and optimal decision-making regarding the operation and maintenance (O&M) of structures provides impetus to the development of structural health monitoring (SHM) systems. A probabilistic risk-based framework for decision-making has already been proposed. However, in order to learn the statistical models necessary for decision-making, measured data from the structure of interest are required. Unfortunately, these data are seldom available across the range of environmental and operational conditions necessary to ensure good generalisation of the model. Recently, technologies have been developed that overcome this challenge, by extending SHM to populations of structures, such that valuable knowledge may be transferred between instances of structures that are sufficiently similar. This new approach is termed population-based structural heath monitoring (PBSHM). The current paper presents a formal representation of populations of structures, such that risk-based decision processes may be specified within them. The population-based representation is an extension to the hierarchical representation of a structure used within the probabilistic risk-based decision framework to define fault trees. The result is a series, consisting of systems of systems ranging from the individual component level up to an inventory of heterogeneous populations. The current paper considers an inventory of wind farms as a motivating example and highlights the inferences and decisions that can be made within the hierarchical representation.

Every novel technology adds hidden vulnerabilities ready to be exploited by a growing number of cyber-attacks. Automated software testing can be a promising solution to quickly analyze thousands of lines of code by generating and slightly modifying function-specific testing data to encounter a multitude of vulnerabilities and attack vectors. This process draws similarities to the constrained adversarial examples generated by adversarial learning methods, so there could be significant benefits to the integration of these methods in automated testing tools. Therefore, this systematic review is focused on the current state-of-the-art of constrained data generation methods applied for adversarial learning and software testing, aiming to guide researchers and developers to enhance testing tools with adversarial learning methods and improve the resilience and robustness of their digital systems. The found constrained data generation applications for adversarial machine learning were systematized, and the advantages and limitations of approaches specific for software testing were thoroughly analyzed, identifying research gaps and opportunities to improve testing tools with adversarial attack methods.

Physics-informed Neural Networks (PINNs) have been widely used to obtain accurate neural surrogates for a system of Partial Differential Equations (PDE). One of the major limitations of PINNs is that the neural solutions are challenging to interpret, and are often treated as black-box solvers. While Symbolic Regression (SR) has been studied extensively, very few works exist which generate analytical expressions to directly perform SR for a system of PDEs. In this work, we introduce an end-to-end framework for obtaining mathematical expressions for solutions of PDEs. We use a trained PINN to generate a dataset, upon which we perform SR. We use a Differentiable Program Architecture (DPA) defined using context-free grammar to describe the space of symbolic expressions. We improve the interpretability by pruning the DPA in a depth-first manner using the magnitude of weights as our heuristic. On average, we observe a 95.3% reduction in parameters of DPA while maintaining accuracy at par with PINNs. Furthermore, on an average, pruning improves the accuracy of DPA by 7.81% . We demonstrate our framework outperforms the existing state-of-the-art SR solvers on systems of complex PDEs like Navier-Stokes: Kovasznay flow and Taylor-Green Vortex flow. Furthermore, we produce analytical expressions for a complex industrial use-case of an Air-Preheater, without suffering from performance loss viz-a-viz PINNs.

Demonstrations provide insight into relevant state or action space regions, bearing great potential to boost the efficiency and practicality of reinforcement learning agents. In this work, we propose to leverage demonstration datasets by combining skill learning and sequence modeling. Starting with a learned joint latent space, we separately train a generative model of demonstration sequences and an accompanying low-level policy. The sequence model forms a latent space prior over plausible demonstration behaviors to accelerate learning of high-level policies. We show how to acquire such priors from state-only motion capture demonstrations and explore several methods for integrating them into policy learning on transfer tasks. Our experimental results confirm that latent space priors provide significant gains in learning speed and final performance. We benchmark our approach on a set of challenging sparse-reward environments with a complex, simulated humanoid, and on offline RL benchmarks for navigation and object manipulation. Videos, source code and pre-trained models are available at the corresponding project website at https://facebookresearch.github.io/latent-space-priors .

The modeling and uncertainty quantification of closed curves is an important problem in the field of shape analysis, and can have significant ramifications for subsequent statistical tasks. Many of these tasks involve collections of closed curves, which often exhibit structural similarities at multiple levels. Modeling multiple closed curves in a way that efficiently incorporates such between-curve dependence remains a challenging problem. In this work, we propose and investigate a multiple-output (a.k.a. multi-output), multi-dimensional Gaussian process modeling framework. We illustrate the proposed methodological advances, and demonstrate the utility of meaningful uncertainty quantification, on several curve and shape-related tasks. This model-based approach not only addresses the problem of inference on closed curves (and their shapes) with kernel constructions, but also opens doors to nonparametric modeling of multi-level dependence for functional objects in general.

These authors contributed equally to this work. Abstract The growing renewable energy sources have posed significant challenges to traditional power scheduling. It is difficult for operators to obtain accurate day-ahead forecasts of renewable generation, thereby requiring the future scheduling system to make real-time scheduling decisions aligning with ultra-short-term forecasts. Restricted by the computation speed, traditional optimization-based methods can not solve this problem. Recent developments in reinforcement learning (RL) have demonstrated the potential to solve this challenge. However, the existing RL methods are inadequate in terms of constraint complexity, algorithm performance, and environment fidelity. The proposed approach enables planning and finer time resolution adjustments of power generators, including unit commitment and economic dispatch, thus increasing the grid's ability to admit more renewable energy. The well-trained scheduling agent significantly reduces renewable curtailment and load shedding, which are issues arising from traditional scheduling's reliance on inaccurate day-ahead forecasts. High-frequency control decisions exploit the existing units' flexibility, reducing the power grid's dependence on hardware transformations and saving investment and operating costs, as demonstrated in experimental results. This research exhibits the potential of reinforcement learning in promoting low-carbon and intelligent power systems and represents a solid step toward sustainable electricity generation. Climate change and carbon neutrality have garnered widespread global attention. The significant amount of carbon emissions during electricity production underscores the importance of achieving low-carbon electricity production as a solution to these pressing challenges. In recent years, wind and solar energy have emerged as promising sources of sustainable electricity. However, the fluctuation patterns of these sources are highly variable, making it challenging to accurately predict their power generation capacity over the long term. This presents a major challenge for existing power scheduling systems that rely on reliable long-term forecasts and day-ahead calculation, potentially leading to suboptimal or infeasible solutions, including renewable curtailments and blackouts [1, 2]. Traditionally, power system operators perform the day-ahead scheduling (DAS) program to calculate power generation schedules [3].

In the 1990s, business process reengineering was all the rage: Companies used budding technologies such as enterprise resource planning (ERP) systems and the internet to enact radical changes to broad, end-to-end business processes. Buoyed by reengineering's academic and consulting proponents, companies anticipated transformative changes to broad processes like order-to-cash and conception to commercialization of new products. But while technology did bring major updates, implementations often failed to live up to the sky-high expectations. For example, large-scale ERP systems like SAP or Oracle provided a useful IT backbone to exchange data, yet also created very rigid processes that were hard to change past the IT implementation. Since then, process management typically involved only incremental change to local processes -- Lean and Six Sigma for repetitive processes, and Agile Lean Startup methods for development -- all without any assistance from technology.