Energy arbitrage is one of the most profitable sources of income for battery operators, generating revenues by buying and selling electricity at different prices. Forecasting these revenues is challenging due to the inherent uncertainty of electricity prices. Deep reinforcement learning (DRL) emerged in recent years as a promising tool, able to cope with uncertainty by training on large quantities of historical data. However, without access to future electricity prices, DRL agents can only react to the currently observed price and not learn to plan battery dispatch. Therefore, in this study, we combine DRL with time-series forecasting methods from deep learning to enhance the performance on energy arbitrage. We conduct a case study using price data from Alberta, Canada that is characterized by irregular price spikes and highly non-stationary. This data is challenging to forecast even when state-of-the-art deep learning models consisting of convolutional layers, recurrent layers, and attention modules are deployed. Our results show that energy arbitrage with DRL-enabled battery control still significantly benefits from these imperfect predictions, but only if predictors for several horizons are combined. Grouping multiple predictions for the next 24-hour window, accumulated rewards increased by 60% for deep Q-networks (DQN) compared to the experiments without forecasts. We hypothesize that multiple predictors, despite their imperfections, convey useful information regarding the future development of electricity prices through a "majority vote" principle, enabling the DRL agent to learn more profitable control policies.

This week, Emily Bazelon, John Dickerson, and David Plotz discuss Donald Trump's fascism, disinhibition, and age; the state of young men in America with Rachel Simmons; and Diversity, Equity, and Inclusion at the University of Michigan with Nicholas Confessore of The New York Times. Tickets are on sale now. And send us your Conundrums at slate.com/conundrum. Here are some notes and references from this week's show: Jeffrey Goldberg for The Atlantic: Trump: 'I Need The Kind Of Generals That Hitler Had' ABC News: Kamala Harris reacts to John Kelly's remarks that Trump is a'fascist' and CNN: Harris says she believes Trump is a fascist: Part 1 of Kamala Harris' Town Hall Niall Stanage for The Hill: What we know, and what we don't, about early voting numbers Nicholas Confessore for The New York Times: The University of Michigan Doubled Down on D.E.I. What Went Wrong? and Anna Betts: What to Know About State Laws That Limit or Ban D.E.I.

In iOS 18.2, Apple is adding a new feature that resurrects some of the intent behind its halted CSAM scanning plans -- this time, without breaking end-to-end encryption or providing government backdoors. Rolling out first in Australia, the company's expansion of its Communication Safety feature uses on-device machine learning to detect and blur nude content, adding warnings and requiring confirmation before users can proceed. If the child is under 13, they can't continue without entering the device's Screen Time passcode. If the device's onboard machine learning detects nude content, the feature automatically blurs the photo or video, displays a warning that the content may be sensitive and offers ways to get help. The choices include leaving the conversation or group thread, blocking the person and accessing online safety resources.

Meta's new AI chatbot has finally started rolling out in the UK, letting users access titbits of information and even create fake images. But MailOnline's first experience with the AI bot suggests Mark Zuckerberg's technology may have a deep-seated gender bias. We asked Meta AI 10 image prompts – including'show me a picture of a receptionist' and'show me a picture of a doctor'. The results revealed that CEOs, builders, doctors, electricians, politicians, physicists, footballers, journalists and'leaders' were all depicted all as men. Meanwhile, nurses, receptionists and beauticians were shown as women – conforming with existing gender stereotypes in the workplace.

Very few Yugoslavians had access to computers in the early 1980s: they were mostly the preserve of large institutions or companies. Importing home computers like the Commodore 64 was not only expensive, but also legally impossible, thanks to a law that restricted regular citizens from importing individual goods that were worth more than 50 Deutsche Marks (the Commodore 64 cost over 1,000 Deutsche Marks at launch). Even if someone in Yugoslavia could afford the latest home computers, they would have to resort to smuggling. In 1983, engineer Vojislav "Voja" Antonić was becoming more and more frustrated with the senseless Yugoslavian import laws. "We had a public debate with politicians," he says.

Autonomous agents require the capability to identify dynamic objects in their environment for safe planning and navigation. Incomplete and erroneous dynamic detections jeopardize the agent's ability to accomplish its task. Dynamic detection is a challenging problem due to the numerous sources of uncertainty inherent in the problem's inputs and the wide variety of applications, which often lead to use-case-tailored solutions. We propose a robust learning-free approach to segment moving objects in point cloud data. The foundation of the approach lies in modelling each voxel using a hidden Markov model (HMM), and probabilistically integrating beliefs into a map using an HMM filter. The proposed approach is tested on benchmark datasets and consistently performs better than or as well as state-of-the-art methods with strong generalized performance across sensor characteristics and environments. The approach is open-sourced at https://github.com/vb44/HMM-MOS.

Although recent advancements in end-to-end learning-based link prediction (LP) methods have shown remarkable capabilities, the significance of traditional similarity-based LP methods persists in unsupervised scenarios where there are no known link labels. However, the selection of node features for similarity computation in similarity-based LP can be challenging. Less informative node features can result in suboptimal LP performance. To address these challenges, we integrate self-supervised graph learning techniques into similarity-based LP and propose a novel method: Self-Supervised Similarity-based LP (3SLP). 3SLP is suitable for the unsupervised condition of similarity-based LP without the assistance of known link labels. Specifically, 3SLP introduces a dual-view contrastive node representation learning (DCNRL) with crafted data augmentation and node representation learning. DCNRL is dedicated to developing more informative node representations, replacing the node attributes as inputs in the similarity-based LP backbone. Extensive experiments over benchmark datasets demonstrate the salient improvement of 3SLP, outperforming the baseline of traditional similarity-based LP by up to 21.2% (AUC).

Numerous Optimization Algorithms have a time-varying update rule thanks to, for instance, a changing step size, momentum parameter or, Hessian approximation. In this paper, we apply unrolled or automatic differentiation to a time-varying iterative process and provide convergence (rate) guarantees for the resulting derivative iterates. We adapt these convergence results and apply them to proximal gradient descent with variable step size and FISTA when solving partly smooth problems. We confirm our findings numerically by solving $\ell_1$ and $\ell_2$-regularized linear and logisitc regression respectively. Our theoretical and numerical results show that the convergence rate of the algorithm is reflected in its derivative iterates.

Coordinated reply attacks are a tactic observed in online influence operations and other coordinated campaigns to support or harass targeted individuals, or influence them or their followers. Despite its potential to influence the public, past studies have yet to analyze or provide a methodology to detect this tactic. In this study, we characterize coordinated reply attacks in the context of influence operations on Twitter. Our analysis reveals that the primary targets of these attacks are influential people such as journalists, news media, state officials, and politicians. We propose two supervised machine-learning models, one to classify tweets to determine whether they are targeted by a reply attack, and one to classify accounts that reply to a targeted tweet to determine whether they are part of a coordinated attack. The classifiers achieve AUC scores of 0.88 and 0.97, respectively. These results indicate that accounts involved in reply attacks can be detected, and the targeted accounts themselves can serve as sensors for influence operation detection.

In neuroscience, researchers typically conduct experiments under multiple conditions to acquire neural responses in the form of high-dimensional spike train datasets. Analysing high-dimensional spike data is a challenging statistical problem. To this end, Gaussian process factor analysis (GPFA), a popular class of latent variable models has been proposed. GPFA extracts smooth, low-dimensional latent trajectories underlying high-dimensional spike train datasets. However, such analyses are often done separately for each experimental condition, contrary to the nature of neural datasets, which contain recordings under multiple experimental conditions. Exploiting the parametric nature of these conditions, we propose a multi-condition GPFA model and inference procedure to learn the underlying latent structure in the corresponding datasets in sample-efficient manner. In particular, we propose a non-parametric Bayesian approach to learn a smooth tuning function over the experiment condition space. Our approach not only boosts model accuracy and is faster, but also improves model interpretability compared to approaches that separately fit models for each experimental condition.