Reasoning is central to human intelligence. However, fallacious arguments are common, and some exacerbate problems such as spreading misinformation about climate change. In this paper, we propose the task of logical fallacy detection, and provide a new dataset (Logic) of logical fallacies generally found in text, together with an additional challenge set for detecting logical fallacies in climate change claims (LogicClimate). Detecting logical fallacies is a hard problem as the model must understand the underlying logical structure of the argument. We find that existing pretrained large language models perform poorly on this task. In contrast, we show that a simple structure-aware classifier outperforms the best language model by 5.46% on Logic and 4.51% on LogicClimate. We encourage future work to explore this task as (a) it can serve as a new reasoning challenge for language models, and (b) it can have potential applications in tackling the spread of misinformation. Our dataset and code are available at https://github.com/causalNLP/logical-fallacy

Estimating the causal effects of a spatially-varying intervention on a spatially-varying outcome may be subject to non-local confounding (NLC), a phenomenon that can bias estimates when the treatments and outcomes of a given unit are dictated in part by the covariates of other nearby units. In particular, NLC is a challenge for evaluating the effects of environmental policies and climate events on health-related outcomes such as air pollution exposure. This paper first formalizes NLC using the potential outcomes framework, providing a comparison with the related phenomenon of causal interference. Then, it proposes a broadly applicable framework, termed "weather2vec", that uses the theory of balancing scores to learn representations of non-local information into a scalar or vector defined for each observational unit, which is subsequently used to adjust for confounding in conjunction with causal inference methods. The framework is evaluated in a simulation study and two case studies on air pollution where the weather is an (inherently regional) known confounder.

In order to avoid conventional controlling methods which created obstacles due to the complexity of systems and intense demand on data density, developing modern and more efficient control methods are required. In this way, reinforcement learning off-policy and model-free algorithms help to avoid working with complex models. In terms of speed and accuracy, they become prominent methods because the algorithms use their past experience to learn the optimal policies. In this study, three reinforcement learning algorithms; DDPG, TD3 and SAC have been used to train Fetch robotic manipulator for four different tasks in MuJoCo simulation environment. All of these algorithms are off-policy and able to achieve their desired target by optimizing both policy and value functions. In the current study, the efficiency and the speed of these three algorithms are analyzed in a controlled environment.

Hoist scheduling has become a bottleneck in electroplating industry applications with the development of autonomous devices. Although there are a few approaches proposed to target at the challenging problem, they generally cannot scale to large-scale scheduling problems. In this paper, we formulate the hoist scheduling problem as a new temporal planning problem in the form of adapted PDDL, and propose a novel hierarchical temporal planning approach to efficiently solve the scheduling problem. Additionally, we provide a collection of real-life benchmark instances that can be used to evaluate solution methods for the problem. We exhibit that the proposed approach is able to efficiently find solutions of high quality for large-scale real-life benchmark instances, with comparison to state-of-the-art baselines.

Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications, and in particular for visuo-motor control. Model-based RL has the potential to be highly sample efficient by concurrently learning a world model and using synthetic rollouts for planning and policy improvement. However, in practice, sample-efficient learning with model-based RL is bottlenecked by the exploration challenge. In this work, we find that leveraging just a handful of demonstrations can dramatically improve the sample-efficiency of model-based RL. Simply appending demonstrations to the interaction dataset, however, does not suffice. We identify key ingredients for leveraging demonstrations in model learning -- policy pretraining, targeted exploration, and oversampling of demonstration data -- which forms the three phases of our model-based RL framework. We empirically study three complex visuo-motor control domains and find that our method is 150%-250% more successful in completing sparse reward tasks compared to prior approaches in the low data regime (100K interaction steps, 5 demonstrations). Code and videos are available at: https://nicklashansen.github.io/modemrl

In 2013, Jeff Bezos announced Amazon was developing a drone delivery service. He estimated at the time that air-dropped packages were "four, five years" away. Nearly a decade later, the service is promised to begin by the end of this year – albeit in only two locations in the US. According to David Carbon, an Australian expat and vice-president of the firm's drone delivery division, Amazon wants to deliver 500m packages annually by drone from 2030. Carbon told AAP earlier this month that the firm was planning a wider rollout for air deliveries in the US and potentially Australia.

As the effects of climate change become more apparent, there is an urgent need to find solutions that can help to reduce greenhouse gas emissions and slow the pace of global warming. One technology that is gaining attention in this effort is machine learning, which has the potential to help us understand and address some of the most pressing challenges facing our planet. One of the key ways that machine learning can help in the fight against climate change is by providing us with insights and predictions that can inform decision making and policy. For example, machine learning algorithms can be used to analyze data on global temperatures, atmospheric carbon dioxide levels, and other environmental indicators, providing us with a better understanding of the current state of the planet and the likely impacts of different actions. Machine learning can also be used to optimize processes and systems in ways that reduce greenhouse gas emissions.

The past three months alone has seen the UK announce three major milestones – covering carbon storage, offshore wind and hybrid energy projects – to propel it further down the road towards net zero. But that journey is no longer only about creating a sustainable, green future. World events have brought security of supply sharply into focus, placing new impetus on governments to accelerate alternative energy projects. While moving at pace is critical for the planet, the old proverb of more haste, less speed – warning against making errors by acting too quickly and without due diligence – should be weighing on the minds of developers. Nicola Blanshard, CEO of Geoteric, a world-leading AI-driven seismic interpretation software provider, believes the balance of speed and success can be achieved through appropriate application of technology. She explained: "The need for alternative energy sources beyond hydrocarbons is well understood, and a massive expansion of carbon storage and offshore wind projects will be required to meet the Paris Agreement targets.

NXP is using Electra Vehicles' EVE-Ai 360 Adaptive Controls technology to use digital twin models in the cloud to predict and control the physical BMS in real time, to improve battery performance, battery state of health of up to 12% and enable multiple new applications, such as EV fleet management. Batteries remain the costliest element in an electric vehicle (EV), and AI-powered digital twin cloud services have the potential to improve estimations of the battery's state of health (SOH) and state of charge (SOC) to deliver improved efficiency, lifetime and cost. Battery digital twins adapt to ongoing changes in battery health due to operating conditions and provide updated figures back to the BMS for continuously improving control decisions. Carmakers can use the technology to provide driver insights, such as range and speed recommendations. In addition, adaptive battery control can improve the battery's performance and safely extend its lifespan, reducing warranty costs for the carmaker.

Join Kayrros, a fast-growing startup using artificial intelligence to transform the world's biggest industries. Kayrros is a leading data analytics company that monitors and measures energy, natural resources, and industrial activity using proprietary algorithms. We combine satellite imagery, data science and advanced mathematics to create unique insights and customer-specific solutions for better decision-making. Our team of experts and tech wizards are working to bring transparency to energy and the environment, from crude oil tank volumes to methane emissions. In just five years, the Kayrros team has grown to include 140 experts in data science, mathematics and energy, representing over 20 nationalities and 10 spoken languages.