Neural architecture search (NAS) finds high performing networks for a given task. Yet the results of NAS are fairly prosaic; they did not e.g. This is not least because the search spaces in NAS often aren't diverse enough to include such transformations a priori. Instead, for NAS to provide greater potential for fundamental design shifts, we need a novel expressive search space design which is built from more fundamental operations. To this end, we introduce einspace, a search space based on a parameterised probabilistic context-free grammar.

Movement primitives (MPs) are compact representations of robot skills that can be learned from demonstrations and combined into complex behaviors. However, merely equipping robots with a fixed set of innate MPs is insufficient to deploy them in dynamic and unpredictable environments. Instead, the full potential of MPs remains to be attained via adaptable, large-scale MP libraries. In this paper, we propose a set of seven fundamental operations to incrementally learn, improve, and re-organize MP libraries. To showcase their applicability, we provide explicit formulations of the spatial operations for libraries composed of Via-Point Movement Primitives (VMPs). By building on Riemannian manifold theory, our approach enables the incremental learning of all parameters of position and orientation VMPs within a library. Moreover, our approach stores a fixed number of parameters, thus complying with the essential principles of incremental learning. We evaluate our approach to incrementally learn a VMP library from motion capture data provided sequentially.

The next generation of high-performance, low-power computer systems might be inspired by the brain. However, as designers move away from conventional computer technology towards brain-inspired (neuromorphic) systems, they must also move away from the established formal hierarchy that underpins conventional machines -- that is, the abstract framework that broadly defines how software is processed by a digital computer and converted into operations that run on the machine's hardware. This hierarchy has helped enable the rapid growth in computer performance. Writing in Nature, Zhang et al.1 define a new hierarchy that formalizes the requirements of algorithms and their implementation on a range of neuromorphic systems, thereby laying the foundations for a structured approach to research in which algorithms and hardware for brain-inspired computers can be designed separately. The performance of conventional digital computers has improved over the past 50 years in accordance with Moore's law, which states that technical advances will enable integrated circuits (microchips) to double their resources approximately every 18–24 months.

Recently, researchers from DeepMind and McGill University proposed new approaches to speed up the solution of complex reinforcement learning problems. They mainly introduced a divide and conquer approach to reinforcement learning (RL), which is combined with deep learning to scale up the potentials of the agents. For a few years now, reinforcement learning has been providing a conceptual framework in order to address several fundamental problems. This algorithm has been utilised in several applications, such as to model robots, simulate artificial limbs, developing self-driving cars, play games like poker, Go, and more. Also, the recent combination of reinforcement learning with deep learning added several impressive achievements and is found to be a promising approach to tackle important sequential decision-making problems that are currently intractable.