Goal-conditioned reinforcement learning is a powerful way to control an AI agent's behavior at runtime. That said, popular goal representations, e.g., target states or natural language, are either limited to Markovian tasks or rely on ambiguous task semantics. We propose representing temporal goals using compositions of deterministic finite automata (cDFAs) and use cDFAs to guide RL agents. cDFAs balance the need for formal temporal semantics with ease of interpretation: if one can understand a flow chart, one can understand a cDFA. On the other hand, cDFAs form a countably infinite concept class with Boolean semantics, and subtle changes to the automaton can result in very different tasks, making them difficult to condition agent behavior on. To address this, we observe that all paths through a DFA correspond to a series of reach-avoid tasks and propose pre-training graph neural network embeddings on "reach-avoid derived" DFAs. Through empirical evaluation, we demonstrate that the proposed pre-training method enables zero-shot generalization to various cDFA task classes and accelerated policy specialization without the myopic suboptimality of hierarchical methods.

The state of health (SOH) of a Li-ion battery is a critical parameter that determines the remaining capacity and the remaining lifetime of the battery. In this paper, we propose SambaMixer a novel structured state space model (SSM) for predicting the state of health of Li-ion batteries. The proposed SSM is based on the MambaMixer architecture, which is designed to handle multi-variate time signals. We evaluate our model on the NASA battery discharge dataset and show that our model outperforms the state-of-the-art on this dataset. We further introduce a novel anchor-based resampling method which ensures time signals are of the expected length while also serving as augmentation technique. Finally, we condition prediction on the sample time and the cycle time difference using positional encodings to improve the performance of our model and to learn recuperation effects. Our results proof that our model is able to predict the SOH of Li-ion batteries with high accuracy and robustness.

The Fox News Health Newsletter brings you trending and important stories about health care, drug developments, mental health issues, real people's triumphs over medical struggles, and more.

Meta's blowout year continues after the company reported another stellar financial quarter on Wednesday. But shares fell in after-hours trading after the company missed Wall Street expectations for daily active users. Wall Street analysts had high expectations for the Instagram and WhatsApp parent company, projecting an 18% jump in sales year over year. The company reported 40.6bn in sales, a 19% increase year over year that outpaced investor expectations of 40.19bn. Meta, which saw a 25% jump in its share price over the past two months, reported 6.03 in earnings per share (EPS), surpassing Wall Street's expectations of an EPS of 5.29.

Elon Musk just dragged ChatGPT and other artificial intelligence programs into the Trump crosshairs by repeating his warning that current AI models are too "woke" and "politically correct." "A lot of the AIs that are being trained in the San Francisco Bay Area, they take on the philosophy of people around them," Musk said at the Future Investment Initiative, a Saudi Arabia government–backed event held in Riyadh this week. "So you have a woke, nihilistic--in my opinion--philosophy that is being built into these AIs." Although Musk is himself a polarizing figure, he is right about AI systems harboring political biases. The issue, however, is far from one-sided, and Musk's framing may help further his own interests due to his ties to Trump.

The US presidential election is in its final stretch. Before election day on November 5, Engadget is looking at where the candidates, Kamala Harris and Donald Trump, stand on the most consequential tech issues of our day. While it might not garner the headlines that immigration, abortion or inflation do, AI is quietly one of the more consequential issues this election season. What regulations are put in place and how forcefully those rules are enforced will have wide ranging impacts on consumer privacy, intellectual property, the media industry and national security. Normally, politicians lack clear or coherent policies on emerging technologies.

"I lost count after 100," the 44-year-old, camouflage-clad instructor told Al Jazeera while observing three cadets of his drone flight school pilot their buzzing aircraft over a withering meadow just outside Kyiv. Sitting at a plastic table littered with tools and batteries, the cadets with their joysticks and goggle cameras looked geeky and harmless. During their Saturday morning drill, each of them took turns flying a drone whose camera allows first-person views of the flight. Time after time after time, the cadets learned how to manoeuvre their drones by flying them through two loops stuck into the wet ground. The drones often fell with a whiz after touching a loop or a bush, losing a red plastic propeller or a leg that had to be found in the wet grass and reattached.

Vice President Harris pledges a new path forward, invokes Jan. 6 and reminds supporters that America knows what kind of leader former President Trump is in speech at the Ellipse in Washington, D.C. Vice President Kamala Harris, who has indicated that she would be willing to undergo a cognitive test, has also suggested that under a Harris administration, the U.S. would swiftly remove individuals who illegally enter the country, "prosecute the cartels," and provide Border Patrol with needed support. "CBS Evening News" anchor and managing editor Norah O'Donnell confronted Harris about former President Donald Trump's claim that the vice president is "a very low-IQ person" who should undergo a test. "Would you take a cognitive test?" O'Donnell asked. "Sure," Harris responded, adding, "I would challenge him to take the same one." She claimed that Trump "is increasingly unstable and unhinged."

This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data. With language as a medium, our method adaptively integrates social events into forecasting models, aligning news content with time series fluctuations to provide richer insights. Specifically, we utilize LLM-based agents to iteratively filter out irrelevant news and employ human-like reasoning to evaluate predictions. This enables the model to analyze complex events, such as unexpected incidents and shifts in social behavior, and continuously refine the selection logic of news and the robustness of the agent's output. By integrating selected news events with time series data, we fine-tune a pre-trained LLM to predict sequences of digits in time series. The results demonstrate significant improvements in forecasting accuracy, suggesting a potential paradigm shift in time series forecasting through the effective utilization of unstructured news data.

While traditional methods, such as the finite element method, provide reliable solutions, their accuracy is often tied to the use of computationally intensive fine meshes. Moreover, they do not naturally account for measurements or prior solutions, and any change in the problem parameters requires results to be fully recomputed. They can also integrate prior knowledge and tackle entire families of PDEs by simply aggregating additional training losses. Nevertheless, they are highly sensitive to hyperparameters such as collocation points and the weights associated with each loss. It demonstrates that finding a (weak) solution of a PDE is equivalent to solving a constrained learning problem with worst-case losses. This explains the limitations of previous methods that minimize the expected value of aggregated losses. SCL also organically integrates structural constraints (e.g., invariances) and (partial) measurements or known solutions. The resulting constrained learning problems can be tackled using a practical algorithm that yields accurate solutions across a variety of PDEs, neural network architectures, and prior knowledge levels without extensive hyperparameter tuning and sometimes even at a lower computational cost. As such, a variety of numerical methods have been used to approximate their solutions, such as the celebrated finite element method (FEM). Despite their approximation guarantees, the accuracy of these methods is often in proportion to the computational complexity associated with finer discretizations. Additionally, they do not naturally incorporate prior knowledge, such as real-world measurements or previous solutions to similar equations. Lastly, any change to the PDE problem, such as initial condition or mesh size, requires the solution to be recomputed (Brenner & Scott, 2007; LeVeque, 2007; Katsikadelis, 2016). Methods based on neural network (NN) architectures, such as physics-informed NNs (PINNs) (Lagaris et al., 1998; Raissi et al., 2019; Lu et al., 2021b) and neural operators (NOs) (Li et al., 2021; Lu et al., 2021a; Rahman et al., 2023), have been proposed in an attempt to address these challenges. Rather than discretizing the PDE, these mesh-free approaches directly fit NNs to its solution.