Minecraft's ray tracing feature for Windows 10 has made its way out of beta eight months after the feature first became available for testers. The addition of ray tracing support for NVIDIA's RTX graphics cards transforms the sandbox game's aesthetics into one that's, well, shinier. As we said in our hands-on post earlier this year, the realistic lighting, reflections and shadows the feature brings make Minecraft feel more immersive. Yes, the game is still as blocky as ever, but the in-game sunlight looks so real, for instance, and shadows and reflections could make you feel as if you're inside the virtual world. To be able to experience what ray tracing adds to the game, you'll need to run it on a PC with one of NVIDIA's GPUs that's capable of ray tracing.

Decision making under uncertainty is critical to real-world, autonomous systems. Model Predictive Control (MPC) methods have demonstrated favorable performance in practice, but remain limited when dealing with complex probability distributions. In this paper, we propose a generalization of MPC that represents a multitude of solutions as posterior distributions. By casting MPC as a Bayesian inference problem, we employ variational methods for posterior computation, naturally encoding the complexity and multi-modality of the decision making problem. We propose a Stein variational gradient descent method to estimate the posterior directly over control parameters, given a cost function and observed state trajectories. We show that this framework leads to successful planning in challenging, non-convex optimal control problems.

Stock portfolio optimization is the process of constant re-distribution of money to a pool of various stocks. In this paper, we will formulate the problem such that we can apply Reinforcement Learning for the task properly. To maintain a realistic assumption about the market, we will incorporate transaction cost and risk factor into the state as well. On top of that, we will apply various state-of-the-art Deep Reinforcement Learning algorithms for comparison. Since the action space is continuous, the realistic formulation were tested under a family of state-of-the-art continuous policy gradients algorithms: Deep Deterministic Policy Gradient (DDPG), Generalized Deterministic Policy Gradient (GDPG) and Proximal Policy Optimization (PPO), where the former two perform much better than the last one. Next, we will present the end-to-end solution for the task with Minimum Variance Portfolio Theory for stock subset selection, and Wavelet Transform for extracting multi-frequency data pattern. Observations and hypothesis were discussed about the results, as well as possible future research directions.1

Inferring the driving equations of a dynamical system from population or time-course data is important in several scientific fields such as biochemistry, epidemiology, financial mathematics and many others. Despite the existence of algorithms that learn the dynamics from trajectorial measurements there are few attempts to infer the dynamical system straight from population data. In this work, we deduce and then computationally estimate the Fokker-Planck equation which describes the evolution of the population's probability density, based on stochastic differential equations. Then, following the USDL approach, we project the Fokker-Planck equation to a proper set of test functions, transforming it into a linear system of equations. Finally, we apply sparse inference methods to solve the latter system and thus induce the driving forces of the dynamical system. Our approach is illustrated in both synthetic and real data including non-linear, multimodal stochastic differential equations, biochemical reaction networks as well as mass cytometry biological measurements.

We explore the use of deep reinforcement learning to provide strategies for long term scheduling of hydropower production. We consider a use-case where the aim is to optimise the yearly revenue given week-by-week inflows to the reservoir and electricity prices. The challenge is to decide between immediate water release at the spot price of electricity and storing the water for later power production at an unknown price, given constraints on the system. We successfully train a soft actor-critic algorithm on a simplified scenario with historical data from the Nordic power market. The presented model is not ready to substitute traditional optimisation tools but demonstrates the complementary potential of reinforcement learning in the data-rich field of hydropower scheduling.

This paper introduces a novel statistical regression framework that allows the incorporation of consistency constraints. A linear and nonlinear (kernel-based) formulation are introduced, and both imply closed-form analytical solutions. The models exploit all the information from a set of drivers while being maximally independent of a set of auxiliary, protected variables. We successfully illustrate the performance in the estimation of chlorophyll content.

Anomalous change detection (ACD) is an important problem in remote sensing image processing. Detecting not only pervasive but also anomalous or extreme changes has many applications for which methodologies are available. This paper introduces a nonlinear extension of a full family of anomalous change detectors. In particular, we focus on algorithms that utilize Gaussian and elliptically contoured (EC) distribution and extend them to their nonlinear counterparts based on the theory of reproducing kernels' Hilbert space. We illustrate the performance of the kernel methods introduced in both pervasive and ACD problems with real and simulated changes in multispectral and hyperspectral imagery with different resolutions (AVIRIS, Sentinel-2, WorldView-2, and Quickbird). A wide range of situations is studied in real examples, including droughts, wildfires, and urbanization. Excellent performance in terms of detection accuracy compared to linear formulations is achieved, resulting in improved detection accuracy and reduced false-alarm rates. Results also reveal that the EC assumption may be still valid in Hilbert spaces. We provide an implementation of the algorithms as well as a database of natural anomalous changes in real scenarios http://isp.uv.es/kacd.html.

A Photonics researcher at the University of Strathclyde has received a prestigious fellowship to support his development of ultra-fast Artificial Intelligence (AI) technologies for medicine, security and renewable energy. Dr Antonio Hurtado, Senior Lecturer at Strathclyde's Institute of Photonics, is one of 15 recipients of Turing AI Acceleration Fellowships, supported by a £20million government investment and delivered by UK Research and Innovation (UKRI) to lead innovative and creative AI research with transformative impact. Dr Hurtado aims to develop ultrafast yet energy efficient AI systems using photonic devices which operate through low-energy light signals, such as the semiconductor lasers that can be found in mobile phones and supermarket barcode scanners. Dr Hurtado said: "In today's world, the ability to process vast amounts of data fast and efficiently is crucial in sectors such as energy, healthcare and finance. AI systems are key tools to make sense of huge volumes of data but consume very high levels of energy and increasingly contribute to global greenhouse gas emissions. "Operating in a similar way to the biological neurons that process information in the brain, the new photonic devices will be able to process data at high speeds while reducing energy consumption, helping the UK to meet its net zero carbon ambitions by 2050.

Just in time to spite the Radeon RX 6900 XT launch and drive home the fact that AMD lacks a crucial DLSS equivalent, Nvidia announced a flood of news related to ray tracing and Deep Learning Super Sampling on Tuesday. Minecraft's drool-inducing ray tracing capabilities are exiting beta, though a handful of other games are also adding DLSS 2.0. Minecraft's Windows 10 version is an absolute ray tracing showcase. "Ray-traced Minecraft is glorious to behold, completely altering the look and feel of the game--though this low-fi legend can make even the most fearsome graphics cards sweat when you activate the cutting-edge lighting technology," we said when we evaluated Minecraft's ray tracing beta earlier this year. "Like Quake II RTX, this new-look Minecraft is fully path-traced, meaning that all the lighting in the game comes from ray tracing--shadows, lighting, reflections, materials, you name it," we said.

Let us consider a scenario: one night, an executive responsible for operations for a remote downstream oil and gas refinery gets a call from one of their subordinates saying things started acting up ever since they plugged in a USB they brought from home. Multiple processes have become unstable and commands sent to equipment are not executed as requested. Panicking, they say there has been a cyber attack on the supervisory control and data acquisition (SCADA) system. Valves, pumps, and compressors connected to the system are going haywire, and the organisation's legacy systems were not equipped to prevent whatever new malware snuck into the system. Production comes to a halt for two days.