To balance exploration and exploitation, multi-armed bandit algorithms need to conduct inference on the true mean reward of each arm in every time step using the data collected so far. However, the history of arms and rewards observed up to that time step is adaptively collected and there are known challenges in conducting inference with non-iid data. In particular, sample averages, which play a prominent role in traditional upper confidence bound algorithms and traditional Thompson sampling algorithms, are neither unbiased nor asymptotically normal. We propose a variant of a Thompson sampling based algorithm that leverages recent advances in the causal inference literature and adaptively re-weighs the terms of a doubly robust estimator on the true mean reward of each arm -- hence its name doubly-adaptive Thompson sampling. The regret of the proposed algorithm matches the optimal (minimax) regret rate and its empirical evaluation in a semi-synthetic experiment based on data from a randomized control trial of a web service is performed: we see that the proposed doubly-adaptive Thompson sampling has superior empirical performance to existing baselines in terms of cumulative regret and statistical power in identifying the best arm. Further, we extend this approach to contextual bandits, where there are more sources of bias present apart from the adaptive data collection -- such as the mismatch between the true data generating process and the reward model assumptions or the unequal representations of certain regions of the context space in initial stages of learning -- and propose the linear contextual doubly-adaptive Thompson sampling and the non-parametric contextual doubly-adaptive Thompson sampling extensions of our approach.

Scientists are developing a'digital twin' of Earth to predict future events caused by climate change to help world leaders better prepare. Developed by European scientists and ETH Zurich, researchers say the machine learning algorithm will develop and test simulations leading up to 2050. The virtual model will also predict all processes'as realistically as possible,' including the influence of humans on water, food and energy management and the processes in the physical Earth system. Scientists say the digital twin will provide an accurate representation of the past, present and future changes of our real world. The virtual planet is part of a ten-year program by the European Union called Destination Earth that is designed to push Europe to achieve net carbon neutrality by 2050.

Texas A&M University and University of Oklahoma researchers have designed a reinforcement-based algorithm that automates the prediction of underground oil and gas reserves. Texas A&M University (TAMU) and University of Oklahoma researchers have developed a reinforcement-based algorithm that automates forecasting of subterranean properties, enabling accurate prediction of oil and gas reserves. The algorithm focuses on the correct characterization of the underground environment based on rewards accumulated for making correct predictions of pressure and flow anticipated from boreholes. The TAMU team learned that within 10 iterations of reinforcement learning, the algorithm could correctly and rapidly predict the properties of simple subsurface scenarios. TAMU's Siddharth Misra said, "We have turned history matching into a sequential decision-making problem, which has the potential to reduce engineers' efforts, mitigate human bias, and remove the need of large sets of labeled training data."

This approach also mitigates groupthink and conservatism by reducing bias, which in practice means that "people in power will be less likely to give you the benefit of the doubt if you're different. And you respond to that by being more cautious," says Ibarra. And, according to Columbia's McGrath, "the answers to whatever your puzzle is may come from very unexpected places -- it could be a person who normally doesn't have access to power." Make this a routine, not a special exercise. And communicate the strategy -- and the need for change specifically -- in a way that is positive and personal.

A pizza box sized solar panel in orbit is producing enough electricity to power an iPad, according to a succesful test of the technology by the US Navy. The Photovoltaic Radiofrequency Antenna Module (PRAM) was launched in May 2020 attached to a drone that loops around the Earth every 90 minutes and is designed to harness light from the sun to convert to electricity. The 12x12 inch panel is an early experiment for a technology that could one day harness solar radiation from the sun and beam it to anywhere on the Earth. It is designed to make the best use of light in space, which doesn't have to pass through the atmosphere where it loses energy before reaching the ground. The Pentagon one day envisages an array of panels in space that could send power to even the most remote parts of the planet and create a new global power grid.

Artificial intelligence (AI) has been a hot topic for a while now. While it might appear to be a fairly new concept, it's actually been around since the first computer was built back in the 1930s. The concept of AI involves machine learning. Computers could learn and act on data sets without any human programming. Essentially, AI is a computer mimicking the human brain.

Farming is a tough business. Global food demand is surging, with as many as 10 billion mouths to feed by 2050. At the same time, environmental challenges and labor limitations have made the future uncertain for agricultural managers. A new company called Future Acres proposed to enable farmers to do more with less through the power of robots. The company, helmed by CEO Suma Reddy, who previously served as COO and co-founder at Farmself and has held multiple roles and lead companies focused on the agtech space, has created an autonomous, electric agricultural robotic harvest companion named Carry to help farmers gather hand-picked crops faster and with less physical demand. Automation has been playing an increasingly large role in agriculture, and agricultural robots are widely expected to play a critical role in food production going forward.

Researchers from CeADAR, Ireland's national centre for Applied Data Analytics & AI, have developed a system which uses artificial intelligence to accurately predict the amount of renewable energy that will be produced at wind farms. The new tool, FREMI (Forecasting Renewable Energy with Machine Intelligence) is a collaborative project between CeADAR and SSE Airtricity. The €370,000 project took 18 months to complete and was funded by the SEAI National Energy Research Development and Demonstration (RD&D) programme. FREMI is accurate, scalable, reliable, and maintainable, and has already been deployed 21 SSE Airtricity wind farms around Ireland which are owned and operated by its sister company, SSE Renewables. FREMI will also allow energy traders to comply with new market rules imposed by the Integrated Single Electricity Market (ISEM), the wholesale electricity market for the island of Ireland.

This paper presents Learning-based Autonomous Guidance with Robustness, Optimality, and Safety guarantees (LAG-ROS), a real-time robust motion planning algorithm for safety-critical nonlinear systems perturbed by bounded disturbances. The LAG-ROS method consists of three phases: 1) Control Lyapunov Function (CLF) construction via contraction theory; 2) imitation learning of the CLF-based robust feedback motion planner; and 3) its real-time and decentralized implementation with a learning-based model predictive safety filter. For the CLF, we exploit a neural-network-based method of Neural Contraction Metrics (NCMs), which provides a differential Lyapunov function to minimize an upper bound of the steady-state Euclidean distance between perturbed and unperturbed system trajectories. The NCM ensures the perturbed state to stay in bounded error tubes around given desired trajectories, where we sample training data for imitation learning of the NCM-CLF-based robust centralized motion planner. Using local observations in training also enables its decentralized implementation. Simulation results for perturbed nonlinear systems show that the LAG-ROS achieves higher control performance and task success rate with faster execution speed for real-time computation, when compared with the existing real-time robust MPC and learning-based feedforward motion planners.

Efficient simulation of SDEs is essential in many applications, particularly for ergodic systems that demand efficient simulation of both short-time dynamics and large-time statistics. However, locally Lipschitz SDEs often require special treatments such as implicit schemes with small time-steps to accurately simulate the ergodic measure. We introduce a framework to construct inference-based schemes adaptive to large time-steps (ISALT) from data, achieving a reduction in time by several orders of magnitudes. The key is the statistical learning of an approximation to the infinite-dimensional discrete-time flow map. We explore the use of numerical schemes (such as the Euler-Maruyama, a hybrid RK4, and an implicit scheme) to derive informed basis functions, leading to a parameter inference problem. We introduce a scalable algorithm to estimate the parameters by least squares, and we prove the convergence of the estimators as data size increases. We test the ISALT on three non-globally Lipschitz SDEs: the 1D double-well potential, a 2D multi-scale gradient system, and the 3D stochastic Lorenz equation with degenerate noise. Numerical results show that ISALT can tolerate time-step magnitudes larger than plain numerical schemes. It reaches optimal accuracy in reproducing the invariant measure when the time-step is medium-large.