This provides one way of leveraging and combining the advantages of model-free and model-based approaches. Specifically, we differentiate through MPC by using the KKT conditions of the convex approximation at a fixed point of the controller. Using this strategy, we are able to learn the cost and dynamics of a controller via end-to-end learning. Our experiments focus on imitation learning in the pendulum and cartpole domains, where we learn the cost and dynamics terms of an MPC policy class. We show that our MPC policies are significantly more data-efficient than a generic neural network and that our method is superior to traditional system identification in a setting where the expert is unrealizable.

We study adaptive importance sampling (AIS) as an online learning problem and argue for the importance of the trade-off between exploration and exploitation in this adaptation. Borrowing ideas from the bandits literature, we propose Daisee, a partition-based AIS algorithm. We further introduce a notion of regret for AIS and show that Daisee has $\mathcal{O}(\sqrt{T}(\log T)^{\frac{3}{4}})$ cumulative pseudo-regret, where $T$ is the number of iterations. We then extend Daisee to adaptively learn a hierarchical partitioning of the sample space for more efficient sampling and confirm the performance of both algorithms empirically.

We introduce Contrastive Multivariate Singular Spectrum Analysis, a novel unsupervised method for dimensionality reduction and signal decomposition of time series data. By utilizing an appropriate background dataset, the method transforms a target time series dataset in a way that evinces the sub-signals that are enhanced in the target dataset, as opposed to only those that account for the greatest variance. This shifts the goal from finding signals that explain the most variance to signals that matter the most to the analyst. We demonstrate our method on an illustrative synthetic example, as well as show the utility of our method in the downstream clustering of electrocardiogram signals from the public MHEALTH dataset.

Lagrangian data assimilation is a complex problem in oceanic and atmospheric modeling. Tracking drifters in large-scale geophysical flows can involve uncertainty in drifter location, complex inertial effects, and other factors which make comparing them to simulated Lagrangian trajectories from numerical models extremely challenging. Temporal and spatial discretization, factors necessary in modeling large scale flows, also contribute to separation between real and simulated drifter trajectories. The chaotic advection inherent in these turbulent flows tends to separate even closely spaced tracer particles, making error metrics based solely on drifter displacements unsuitable for estimating model parameters. We propose to instead use error in the coherent structure coloring (CSC) field to assess model skill. The CSC field provides a spatial representation of the underlying coherent patterns in the flow, and we show that it is a more robust metric for assessing model accuracy. Through the use of two test cases, one considering spatial uncertainty in particle initialization, and one examining the influence of stochastic error along a trajectory and temporal discretization, we show that error in the coherent structure coloring field can be used to accurately determine single or multiple simultaneously unknown model parameters, whereas a conventional error metric based on error in drifter displacement fails. Because the CSC field enhances the difference in error between correct and incorrect model parameters, error minima in model parameter sweeps become more distinct. The effectiveness and robustness of this method for single and multi-parameter estimation in analytical flows suggests that Lagrangian data assimilation for real oceanic and atmospheric models would benefit from a similar approach.

In this paper, we show that even if artificial intelligence (AI) or machine learning (ML) systems are individually well-aligned with a goal, specific classes of over-optimization failures can create dynamics in multiparty systems that lead to new failure modes. Even specification of noncompetitive or cooperative goals does not necessarily provide any guarantee for the behavior of systems. By outlining how and why these multi-agent failures can occur, the paper hopes to spur system designers to explicitly consider these failure modes in designing systems, and to find approaches for mitigating them. When complex systems are optimized by a single agent, the representation of the system and of the goal used for optimization often lead to failures that can be surprising to the agent's designers. These various failure modes have been referred to as Goodhart's law [1, 2], Campbell's law [3], faulty reward functions [4], distributional shift [4], reward hacking [5], Proxyeconomics[6], and presumably many other terms. Such failure modes are the focus of a significant body of work in AI safety, and progress has been made.

Pizza Hut will not be outdone in the pursuit of over-the-top delivery vehicles. The restaurant chain has teamed up with Toyota to unveil the Tundra Pie Pro, a concept hydrogen fuel cell truck that not only cooks pizzas, but uses a pair of robot arms to move them along the line. The mechanical limbs fetch pre-assembled pizzas, bake them, slice them and slide them into boxes all on their own -- they'll even ring a bell to let you know your meal is ready. The whole process takes about six to seven minutes, suggesting that the truck could bake your pizza while it's on the way to your home, even if you're just a few blocks away. Both the robotic kitchen and the truck itself rely on hydrogen, so you wouldn't have to worry about hurting the planet in the name of a fresh dish.

Applying artificial intelligence to self-driving cars to smooth traffic, reduce fuel consumption, and improve air quality predictions may sound like the stuff of science fiction, but researchers at the Department of Energy's Lawrence Berkeley National Laboratory (Berkeley Lab) have launched two research projects to do just that. In collaboration with UC Berkeley, Berkeley Lab scientists are using deep reinforcement learning, a computational tool for training controllers, to make transportation more sustainable. One project uses deep reinforcement learning to train autonomous vehicles to drive in ways to simultaneously improve traffic flow and reduce energy consumption. A second uses deep learning algorithms to analyze satellite images combined with traffic information from cell phones and data already being collected by environmental sensors to improve air quality predictions. "Thirty percent of energy use in the U.S. is to transport people and goods, and this energy consumption contributes to air pollution, including approximately half of all nitrogen oxide emissions, a precursor to particular matter and ozone – and black carbon (soot) emissions," said Tom Kirchstetter, director of Berkeley Lab's Energy Analysis and Environmental Impacts Division, an adjunct professor at UC Berkeley, and a member of the research team.

Pizza delivery doesn't get any fresher than this. Pizza Hut may be taking its pie-making show on the road. A new automated pizza-making robot prototype that cooks pizzas on the way to customers' homes is set to be unveiled Tuesday at the Specialty Equipment Market Association's annual automotive specialty products show in Las Vegas. The mobile pizza factory, residing in the bed of a zero-emission Toyota Tundra pickup, will get its debut during Toyota's presentation at the SEMA show. Called "The Kitchen," the operation includes a refrigerator, a pair of robotic arms and a portable conveyor oven – all of which run on the truck's hydrogen fuel-cell electric powertrain.

You know when you try to go online at a Starbucks or on an airplane, first you get a little popup that asks you to accept some terms before you can get to the internet? That popup window exists in a sort of netherworld between actual internet connection and being offline–you pick it up via Wi-Fi, but until you click a box, you're not actually online. A team of five developers realized in that gray area was potentially a huge opportunity to save lives. It's an intractable problem during natural disasters: telecommunications networks and power grids are often damaged or overwhelmed; without them, first responders struggle to help survivors, coordinate evacuations, and even count the dead. Project Owl proposes an elegant solution: an AI-powered disaster coordination platform paired with a robust communication network that can reach people even when other connections are down.

These devices, particularly the smart mobile phones have transformed over a period of time from merely communication tools to smart and highly personal devices enabling to assist the users in their variety of day-to-day situations in their daily life. In the real word, users' interest on "Mobile Phones" is more and more than other platforms like "Desktop Computer" or "Tablet Computer" over time [36]. People use mobile phones not only for voice communication between individuals but also for various activities such as applications (mobile apps) using, Internet browsing, emailing, using online social network, instant messaging etc [28]. Recent advances in the sensing capabilities of smart mobile phones make them enable to collect the rich contextual information and users' various activity records with mobile phones through the device logs. These historical mobile phone data are simply as the collection of the past contexts and user's activities with the mobile phones for these past contexts. These are phone call logs [39] having phone call activities, app usages logs [45] having various mobile application usages, mobile phone notification logs [22] having the responses with various notifications from different applications, web logs [13] having Internet browsing activities of the mobile phone users. The main characteristic of such kind of phone log data is that it contains the actual diverse activities of the users in different contexts in their real world life. Modeling smartphone user behaviors by developing various computational machine learning methods (rule-based learning) in order to analyze different behavioral patterns in different contexts, and eventually predict the next behaviors or detect strange behaviors utilizing such mobile phone data, can be used for build- 2 Iqbal H. Sarker*