We identify a fundamental problem in policy gradient-based methods in continuous control. As policy gradient methods require the agent's underlying probability distribution, they limit policy representation to parametric distribution classes. We show that optimizing over such sets results in local movement in the action space and thus convergence to sub-optimal solutions. We suggest a novel distributional framework, able to represent arbitrary distribution functions over the continuous action space. Using this framework, we construct a generative scheme, trained using an off-policy actor-critic paradigm, which we call the Generative Actor Critic (GAC). Compared to policy gradient methods, GAC does not require knowledge of the underlying probability distribution, thereby overcoming these limitations. Empirical evaluation shows that our approach is comparable and often surpasses current state-of-the-art baselines in continuous domains.

State-of-the-art deep learning methods have shown a remarkable capacity to model complex data domains, but struggle with geospatial data. In this paper, we introduce SpaceGAN, a novel generative model for geospatial domains that learns neighbourhood structures through spatial conditioning. We propose to enhance spatial representation beyond mere spatial coordinates, by conditioning each data point on feature vectors of its spatial neighbours, thus allowing for a more flexible representation of the spatial structure. To overcome issues of training convergence, we employ a metric capturing the loss in local spatial autocorrelation between real and generated data as stopping criterion for SpaceGAN parametrization. This way, we ensure that the generator produces synthetic samples faithful to the spatial patterns observed in the input. SpaceGAN is successfully applied for data augmentation and outperforms compared to other methods of synthetic spatial data generation. Finally, we propose an ensemble learning framework for the geospatial domain, taking augmented SpaceGAN samples as training data for a set of ensemble learners. We empirically show the superiority of this approach over conventional ensemble learning approaches and rivaling spatial data augmentation methods, using synthetic and real-world prediction tasks. Our findings suggest that SpaceGAN can be used as a tool for (1) artificially inflating sparse geospatial data and (2) improving generalization of geospatial models.

Microsoft's latest breakthrough could make DNA-based data centers possible

This review considers a problem in the development of mobile robot adhesion methods with vertical surfaces and the appropriate locomotion mechanism design. The evolution of adhesion methods for wall-climbing robots (based on friction, magnetic forces, air pressure, electrostatic adhesion, molecular forces, rheological properties of fluids and their combinations) and their locomotion principles (wheeled, tracked, walking, sliding framed and hybrid) is studied. Wall-climbing robots are classified according to the applications, adhesion methods and locomotion mechanisms. The advantages and disadvantages of various adhesion methods and locomotion mechanisms are analyzed in terms of mobility, noiselessness, autonomy and energy efficiency. Focus is placed on the physical and technical aspects of the adhesion methods and the possibility of combining adhesion and locomotion methods.

Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid. Identifying insights helps analysts understand the collaboration of various parts of the grid so that preventive and correct operations can be taken to avoid potential accidents. Existing solutions for identifying insights in PGPMs are performed manually, which may be laborious and expertise-dependent. In this paper, we propose an interactive insight identification and annotation framework by leveraging an enhanced variational autoencoder (VAE). In particular, a new architecture, DenseU-Hierarchical VAE (DUHiV), is designed to learn representations from large-sized PGPMs, which achieves a significantly tighter evidence lower bound (ELBO) than existing Hierarchical VAEs with a Multilayer Perceptron architecture. Our approach supports modulating the derived representations in an interactive visual interface, discover potential insights and create multi-label annotations. Evaluations using real-world PGPMs datasets show that our framework outperforms the baseline models in identifying and annotating insights.

Spinning up dark matter simulations is computationally expensive so a team of cosmologists are turning to AI models instead. Generative adversarial networks or GANs are good at learning patterns from data and reproducing them in new samples. In this case, the team led by researchers from the Lawrence Berkeley National Laboratory used weak gravitational lensing maps as input to simulate more of the same images as output. They named the model CosmoGAN and have published a paper in Computational Astrophysics and Cosmology earlier this month. Gravitational lensing provides opportunities for scientists to study the effects of dark matter in the universe.

As the world gasps for clean, safe, cheap, and reliable energy, demand from developing countries and the requirements of new usages rises, fueling a backlash against traditional, centralized power sources. As a result, reliance on renewable energy sources continues to grow, and the sector moves from regulation to innovation while its customers transform from passive consumers to demanding prosumers. Technologies such as automation and artificial intelligence will be instrumental in capitalizing on these shifts. But are organizations poised to make a success of them?

Depiction of fusion research on a doughnut-shaped tokamak enhanced by artificial intelligence. Artificial intelligence (AI), a branch of computer science that is transforming scientific inquiry and industry, could now speed the development of safe, clean and virtually limitless fusion energy for generating electricity. A major step in this direction is under way at the U.S. Department of Energy's (DOE) Princeton Plasma Physics Laboratory (PPPL) and Princeton University, where a team of scientists working with a Harvard graduate student is for the first time applying deep learning -- a powerful new version of the machine learning form of AI -- to forecast sudden disruptions that can halt fusion reactions and damage the doughnut-shaped tokamaks that house the reactions. "This research opens a promising new chapter in the effort to bring unlimited energy to Earth," Steve Cowley, director of PPPL, said of the findings (link is external), which are reported in the current issue of Nature magazine. "Artificial intelligence is exploding across the sciences and now it's beginning to contribute to the worldwide quest for fusion power."

Fixed term contract until 1 March 2021 The Royal College of Art is the UK's only entirely postgraduate art and design university. In 2018/19 the College will have some 2,300 students registered for MA, MRes, MPhil and PhD degrees and over 450 permanent academic, technical and administrative staff, with more than 1,000 visiting lecturers and professors. The RCA Robotics Laboratory, recently established and directed by RCA's Academic Leader in Robotics, Dr Sina Sareh, develops new bioinspired technologies for robot mobility, manipulation and attachment in unstructured and extreme environments through funded projects by EPSRC, Innovate UK and industrial partners. Following the Royal College of Art's Strategic Plan 2016-2021, the lab is intended to create significant research and education capacity in robotics by 2020, to support the RCA's ambitious expansion plans in Battersea South including a new robotics facility and new research centres - the most radical transformation of the institution's campus in its 181-year history. Through the Innovate UK's "Robotics and AI: Inspect, Maintain and Repair in Extreme Environments" funding scheme, a research project grant entitled Multi-Platform Inspection, Maintenance & Repair in Extreme Environments (MIMRee) has been awarded to the RCA.

This essay reviews human observer-based methods employed in shark spotting in Muizenberg Beach. It investigates Machine Learning methods for automated shark detection with the aim of enhancing human observation. A questionnaire and interview were used to collect information about shark spotting, the motivation of the actual Shark Spotter program and its limitations. We have defined a list of desirable properties for our model and chosen the adequate mathematical techniques. The preliminary results of the research show that we can expect to extract useful information from shark images despite the geometric transformations that sharks perform, its features do not change. To conclude, we have partially implemented our model; the remaining implementation requires dataset.