Despite advances in hierarchical reinforcement learning, its applications to path planning in autonomous driving on highways are challenging. One reason is that conventional hierarchical reinforcement learning approaches are not amenable to autonomous driving due to its riskiness: the agent must move avoiding multiple obstacles such as other agents that are highly unpredictable, thus safe regions are small, scattered, and changeable over time. To overcome this challenge, we propose a spatially hierarchical reinforcement learning method for state space and policy space. The high-level policy selects not only behavioral sub-policy but also regions to pay mind to in state space and for outline in policy space. Subsequently, the low-level policy elaborates the short-term goal position of the agent within the outline of the region selected by the high-level command. The network structure and optimization suggested in our method are as concise as those of single-level methods. Experiments on the environment with various shapes of roads showed that our method finds the nearly optimal policies from early episodes, outperforming a baseline hierarchical reinforcement learning method, especially in narrow and complex roads. The resulting trajectories on the roads were similar to those of human strategies on the behavioral planning level.

Robots need to be able to learn concepts from their users in order to adapt their capabilities to each user's unique task. But when the robot operates on high-dimensional inputs, like images or point clouds, this is impractical: the robot needs an unrealistic amount of human effort to learn the new concept. To address this challenge, we propose a new approach whereby the robot learns a low-dimensional variant of the concept and uses it to generate a larger data set for learning the concept in the high-dimensional space. This lets it take advantage of semantically meaningful privileged information only accessible at training time, like object poses and bounding boxes, that allows for richer human interaction to speed up learning. We evaluate our approach by learning prepositional concepts that describe object state or multi-object relationships, like above, near, or aligned, which are key to user specification of task goals and execution constraints for robots. Using a simulated human, we show that our approach improves sample complexity when compared to learning concepts directly in the high-dimensional space. We also demonstrate the utility of the learned concepts in motion planning tasks on a 7-DoF Franka Panda robot.

Apple's new-model, top-of-the-line MacBook Pro laptop computer could set you back nearly $4,000 before taxes. But that will seem like a Black Friday steal when a 45-year-old Apple computer goes on sale this week in Monrovia, where it may fetch six figures or more. On Tuesday, John Moran Auctioneers will auction off a functioning Apple-1 computer hand-built by Steve Wozniak, Steve Jobs and others in a Los Altos, Calif., garage in 1976. The system was the rock upon which the trillion-dollar Apple empire was built. In his 2011 biography "Steve Jobs," Walter Isaacson quotes Wozniak as saying of the Apple-1: "We were participating in the biggest revolution that had ever happened, I thought. I was so happy to be a part of it."

While sharks are deadly marine predators, they also seem to attract fish looking for a'spa day' by rubbing against their rough skin. Drone footage recorded by marine biologists at the University of Miami captured frequent incidents of the surprising ritual. Researchers pored over underwater video, photos, drone footage, and even witness reports to find 47 different instances of fish rubbing up against a shark's body at more than a dozen locations around the world. The length of these regimens varied from eight seconds to more than five minutes, and included dozens of incidents of leerfish, also known as garrick, rubbing up against a great white shark, the ultimate oceanic apex predator, in Plettenberg Bay, South Africa. The number of fish chafing against a particular shark varied, too, from one lone swimmer to over 100 at once.

Machine learning has given humanity the ability to run tasks in an automated manner. It enables us to improve what we already do by analyzing a continuous stream of data related to the same task. Machine learning has a wide range of applications in fields ranging from space research to digital marketing. Machine learning is also the foundation of artificial intelligence. We are not yet inundated with machines capable of making decisions on their own.

Apple's new-model, top-of-the-line MacBook Pro laptop computer could set you back nearly $4,000 before taxes. But that will seem like a Black Friday steal when a 45-year-old Apple computer goes on sale this week in Monrovia, where it may fetch six figures or more, even without a 16-inch, high-definition screen and the latest microprocessors. On Tuesday, John Moran Auctioneers will auction off a functioning Apple-1 computer hand-built by Steve Wozniak, Steve Jobs and others in a Los Altos, Calif., garage in 1976. The system was the rock upon which the trillion-dollar Apple empire was built. In his 2011 biography "Steve Jobs," Walter Isaacson quotes Wozniak as saying of the Apple-1: "We were participating in the biggest revolution that had ever happened, I thought. I was so happy to be a part of it."

A digital replica of Earth could help scientists better model the future of our planet and find solutions to problems wrought by climate change. The advanced model, dubbed Digital Twin Earth, is being developed by the European Space Agency (ESA) and its partners based on data and images from Earth-observation satellites and sensors on the ground. To run reliably, the project will require new advanced artificial intelligence algorithms and powerful supercomputers, which are currently being developed. ESA and its partners discussed their progress in the runup to the UN Climate Change Conference COP26, a two-week event that's currently taking place in Glasgow, Scotland. ESA launched the Digital Twin Earth project in 2020 and invited researchers and tech companies from across Europe to present their progress during an event called PhiWeek, which took place Oct. 11 to Oct. 15.

A rootkit is a program (or set of programs) that allows you to hide the presence of malware in the system. Rootkits are often part of multifunctional malware that could have multiple abilities, such as providing attackers with remote access to compromised hosts, intercepting network traffic, spying on users, recording keystrokes, stealing authentication information, or using the host as a base to mine cryptocurrencies and aid in DDoS attacks. The task of the rootkit is to mask this illegitimate activity on the compromised machine. Some rootkits, such as Necurs, Flame and DirtyMoe, are designed to combine both modes of operation and thus work at both levels. They accounted for 31% of the sample.

Higher-order tensor datasets are rising ubiquitously in modern data science applications, for instance, recommendation systems (Baltrunas et al., 2011; Bi et al., 2018), social networks (Bickel and Chen, 2009), genomics (Hore et al., 2016), and neuroimaging (Zhou et al., 2013). Tensor provides effective representation of data structure that classical vector-and matrix-based methods fail to capture. One example is music recommendation system (Baltrunas et al., 2011) that records ratings of songs from users on various contexts. This three-way tensor of user song context allows us to investigate interactions of users and songs in a context-specific manner. Another example is network dataset that records the connections among a set of nodes. Pairwise interactions are often insufficient to capture the complex relationships, whereas multi-way interactions improve the understanding of networks in molecular system (Young et al., 2018) and social networks (Han et al., 2020). In both examples, higher-order tensors represent multi-way interactions in an efficient way. Tensor estimation problem cannot be solved without imposing structures. An appropriate reordering of tensor entries often provides effective representation of the hidden salient structure.

Most existing classification methods aim to minimize the overall misclassification error rate, however, in applications, different types of errors can have different consequences. To take into account this asymmetry issue, two popular paradigms have been developed, namely the Neyman-Pearson (NP) paradigm and cost-sensitive (CS) paradigm. Compared to CS paradigm, NP paradigm does not require a specification of costs. Most previous works on NP paradigm focused on the binary case. In this work, we study the multi-class NP problem by connecting it to the CS problem, and propose two algorithms. We extend the NP oracle inequalities and consistency from the binary case to the multi-class case, and show that our two algorithms enjoy these properties under certain conditions. The simulation and real data studies demonstrate the effectiveness of our algorithms. To our knowledge, this is the first work to solve the multi-class NP problem via cost-sensitive learning techniques with theoretical guarantees. The proposed algorithms are implemented in the R package "npcs" on CRAN.