We address the problem of phase retrieval (PR) from quantized measurements. The goal is to reconstruct a signal from quadratic measurements encoded with a finite precision, which is indeed the case in many practical applications. We develop a rank-1 projection algorithm that recovers the signal subject to ensuring consistency with the measurement, that is, the recovered signal when encoded must yield the same set of measurements that one started with. The rank-1 projection stems from the idea of lifting, originally proposed in the context of PhaseLift. The consistency criterion is enforced using a one-sided quadratic cost. We also determine the probability with which different vectors lead to the same set of quantized measurements, which makes it impossible to resolve them. Naturally, this probability depends on how correlated such vectors are, and how coarsely/finely the measurements get quantized. The proposed algorithm is also capable of incorporating a sparsity constraint on the signal. An analysis of the cost function reveals that it is bounded, both above and below, by functions that are dependent on how well correlated the estimate is with the ground truth. We also derive the Cram\'er-Rao lower bound (CRB) on the achievable reconstruction accuracy. A comparison with the state-of-the- art algorithms shows that the proposed algorithm has a higher reconstruction accuracy and is about 2 to 3 dB away from the CRB. The edge, in terms of the reconstruction signal-to-noise ratio, over the competing algorithms is higher (about 5 to 6 dB) when the quantization is coarse.

For problem solving, making reactive decisions based on problem description is fast but inaccurate, while search-based planning using heuristics gives better solutions but could be exponentially slow. In this paper, we propose a new approach that improves an existing solution by iteratively picking and rewriting its local components until convergence. The rewriting policy employs a neural network trained with reinforcement learning. We evaluate our approach in two domains: job scheduling and expression simplification. Compared to common effective heuristics, baseline deep models and search algorithms, our approach efficiently gives solutions with higher quality.

This robotic Rubik's Cube is the product of a Japanese creator who's documented many of his creative projects on his YouTube channel, Human Controller. Yes, it has a custom 3D-printed core attached to servo motors that are programmed to solve the cube, which is all laid out in this process post here. But when he puts the Rubik's Cube onto the table to run free and solve itself, it really looks like a super nerdy poltergeist is doing his best to impress his seventh grade crush. As much as I want to believe this is the work of a really smart ghost, the self-solving Rubik's Cube is a project that's been years in the making. The cube, which is now the same dimensions as a standard Rubik's Cube, originally started off much bigger (seen here in the version he posted a year ago).

We present Predicted Variables (PVars), an approach to making machine learning (ML) a first class citizen in programming languages. There is a growing divide in approaches to building systems: using human experts (e.g. programming) on the one hand, and using behavior learned from data (e.g. ML) on the other hand. PVars aim to make ML in programming as easy as `if' statements and with that hybridize ML with programming. We leverage the existing concept of variables and create a new type, a predicted variable. PVars are akin to native variables with one important distinction: PVars determine their value using ML when evaluated. We describe PVars and their interface, how they can be used in programming, and demonstrate the feasibility of our approach on three algorithmic problems: binary search, Quicksort, and caches. We show experimentally that PVars are able to improve over the commonly used heuristics and lead to a better performance than the original algorithms. As opposed to previous work applying ML to algorithmic problems, PVars have the advantage that they can be used within the existing frameworks and do not require the existing domain knowledge to be replaced. PVars allow for a seamless integration of ML into existing systems and algorithms. Our PVars implementation currently relies on standard Reinforcement Learning (RL) methods. To learn faster, PVars use the heuristic function, which they are replacing, as an initial function. We show that PVars quickly pick up the behavior of the initial function and then improve performance beyond that without ever performing substantially worse -- allowing for a safe deployment in critical applications.

We realized manipulation of Rubik's cube using a high-speed robot hand with three fingers. The experimental system consists of a high-speed vision and a high-speed robot hand, and the high-speed vision can calculate the center of gravity position and angle of the Rubik's cube at 500 fps. The manipulation realized in this research is a total of three operations, two kinds of regrasping and one-face turning of the Rubik's cube. By combining these three operations all the faces can be turned. In the experiment, these three operations were performed in a row in 1 second and we succeeded in 30 continuous operations in 10 seconds.

Software defined networking (SDN) represents a promising networking architecture that combines central management and network programmability. SDN separates the control plane from the data plane and moves the network management to a central point, called the controller, that can be programmed and used as the brain of the network. Recently, the research community has showed an increased tendency to benefit from the recent advancements in the artificial intelligence (AI) field to provide learning abilities and better decision making in SDN. In this study, we provide a detailed overview of the recent efforts to include AI in SDN. Our study showed that the research efforts focused on three main sub-fields of AI namely: machine learning, meta-heuristics and fuzzy inference systems. Accordingly, in this work we investigate their different application areas and potential use, as well as the improvements achieved by including AI-based techniques in the SDN paradigm.

We study the adaptive sensing problem for the multiple source seeking problem, where a mobile robot must identify the strongest emitters in an environment with background emissions. Background signals may be highly heterogeneous, and can mislead algorithms which are based on receding horizon control, greedy heuristics, or smooth background priors. We propose AdaSearch, a general algorithm for adaptive sensing. AdaSearch combines global trajectory planning with principled confidence intervals in order to concentrate measurements in promising regions while still guaranteeing sufficient coverage of the entire area. Theoretical analysis shows that AdaSearch significantly outperforms a uniform sampling strategy when the distribution of background signals is highly variable. Simulation studies demonstrate that when applied to the problem of radioactive source-seeking, AdaSearch outperforms both uniform sampling and a receding time horizon information-maximization approach based on the current literature. We corroborate these findings with a hardware demonstration, using a small quadrotor helicopter in a motion-capture arena.

Abstract--In this project, we combine AlphaGo algorithm with Curriculum Learning to crack the game of Gomoku. Modifications like Double Networks Mechanism and Winning Value Decay are implemented to solve the intrinsic asymmetry and short-sight of Gomoku. Our final AI AlphaGomoku, through two days' training on a single GPU, has reached humans' playing level. Free style Gomoku is an interesting strategy board game with quite simple rules: two players alternatively place black and white stones on a board with 15 by 15 grids and winner is the one who first reach a line of consecutive five or more stones of his or her color. It is popular among students since it can be played simply with a piece of paper and a pencil to kill the boring class time. It is also popular among computer scientists since Gomoku is a natural playground for many artificial intelligence algorithms.

We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that are parameterized in a way that makes them easily reusable. This diversity and parameterization of low-level skills allows us to find a transferable policy that is able to use combinations and variations of different skills to solve more complex, high-level tasks. In particular, we first use simulation to jointly learn a policy for a set of low-level skills, and a "skill embedding" parameterization which can be used to compose them. Later, we learn high-level policies which actuate the low-level policies via this skill embedding parameterization. The high-level policies encode how and when to reuse the low-level skills together to achieve specific high-level tasks. Importantly, our method learns to control a real robot in joint-space to achieve these high-level tasks with little or no on-robot time, despite the fact that the low-level policies may not be perfectly transferable from simulation to real, and that the low-level skills were not trained on any examples of high-level tasks. We illustrate the principles of our method using informative simulation experiments. We then verify its usefulness for real robotics problems by learning, transferring, and composing free-space and contact motion skills on a Sawyer robot using only joint-space control. We experiment with several techniques for composing pre-learned skills, and find that our method allows us to use both learning-based approaches and efficient search-based planning to achieve high-level tasks using only pre-learned skills.

Abstract--Hanabi is a cooperative card game with hidden information that has won important awards in the industry and received some recent academic attention. A two-track competition of agents for the game will take place in the 2018 CIG conference. In this paper, we develop a genetic algorithm that builds rulebased agents by determining the best sequence of rules from a fixed rule set to use as strategy. In three separate experiments, we remove human assumptions regarding the ordering of rules, add new, more expressive rules to the rule set and independently evolve agents specialized at specific game sizes. As result, we achieve scores superior to previously published research for the mirror and mixed evaluation of agents. Game-playing agents have a long tradition of serving as benchmarks for AI research. However, traditionally most of the focus has been on competitive, perfect information games, such as Checkers [1], Chess [2] and Go [3]. Cooperative games with imperfect information provide an interesting research topic not only due to the added challenges posed to researchers, but also because many modern industrial and commercial applications can be characterized as examples of cooperation between humans and machines in order to achieve a mutual goal in an uncertain environment. In this paper, we address a particularly interesting cooperative game with partial information: Hanabi [4].