In this paper, we try to improve exploration in Blackbox methods, particularly Evolution strategies (ES), when applied to Reinforcement Learning (RL) problems where intermediate waypoints/subgoals are available. Since Evolutionary strategies are highly parallelizable, instead of extracting just a scalar cumulative reward, we use the state-action pairs from the trajectories obtained during rollouts/evaluations, to learn the dynamics of the agent. The learnt dynamics are then used in the optimization procedure to speed-up training. Lastly, we show how our proposed approach is universally applicable by presenting results from experiments conducted on Carla driving and UR5 robotic arm simulators.

In 2019, Greta Gerwig became the latest in a line of writers, directors, and producers to make a pilgrimage to a toy workshop in El Segundo, California. Touring the facility, the Mattel Design Center, has become a rite of passage for Hollywood types who are considering transforming one of the company's products into a movie--a list that now includes such names as J. J. Abrams (Hot Wheels) and Vin Diesel (Rock'Em Sock'Em Robots). The building has hundreds of workspaces for artists, model-makers, and project managers, and it houses elaborate museum-style exhibitions that document the company's history and core products. These displays can help a toy designer find inspiration; they can also offer a "brand immersion"--a crash course in a Mattel property slated for adaptation. When a V.I.P. visits, Richard Dickson, a tall, bespectacled man who is the company's chief operating officer, plays the role of Willy Wonka. He'll show off the sixty-five-year-old machines that are still used to affix fake hair to Barbies; he'll invite you to inspect life-size, road-ready replicas of Hot Wheels cars. The center even boasts a giant rendering of Castle Grayskull, the fearsome ancestral home of He-Man.

We consider dense, associative neural-networks trained by a teacher (i.e., with supervision) and we investigate their computational capabilities analytically, via statistical-mechanics of spin glasses, and numerically, via Monte Carlo simulations. In particular, we obtain a phase diagram summarizing their performance as a function of the control parameters such as quality and quantity of the training dataset, network storage and noise, that is valid in the limit of large network size and structureless datasets: these networks may work in a ultra-storage regime (where they can handle a huge amount of patterns, if compared with shallow neural networks) or in a ultra-detection regime (where they can perform pattern recognition at prohibitive signal-to-noise ratios, if compared with shallow neural networks). Guided by the random theory as a reference framework, we also test numerically learning, storing and retrieval capabilities shown by these networks on structured datasets as MNist and Fashion MNist. As technical remarks, from the analytic side, we implement large deviations and stability analysis within Guerra's interpolation to tackle the not-Gaussian distributions involved in the post-synaptic potentials while, from the computational counterpart, we insert Plefka approximation in the Monte Carlo scheme, to speed up the evaluation of the synaptic tensors, overall obtaining a novel and broad approach to investigate supervised learning in neural networks, beyond the shallow limit, in general.

We consider the problem of learning personalized treatment policies that are externally valid or generalizable: they perform well in other target populations besides the experimental (or training) population from which data are sampled. We first show that welfare-maximizing policies for the experimental population are robust to shifts in the distribution of outcomes (but not characteristics) between the experimental and target populations. We then develop new methods for learning policies that are robust to shifts in outcomes and characteristics. In doing so, we highlight how treatment effect heterogeneity within the experimental population affects the generalizability of policies. Our methods may be used with experimental or observational data (where treatment is endogenous). Many of our methods can be implemented with linear programming.

Achieving cooperative transportation by teams of aerial robots has been attracting attention owing to its flexibility with respect to payloads and robustness against failures. In this paper, we propose a flexible decentralized controller for the number of robots and the shapes of payloads in a cooperative transport task using multiple single-rotor robots. Our controller is robust to mass and center of mass fluctuations and robot failures. Moreover, asymptotic stability against dynamics errors is guaranteed. Additionally, the controller supports heterogeneous single-rotor robots. Thus, robots with different specifications and deterioration can be effectively utilized for cooperative transportation. In particular, this performance is effective for robot reuse. To achieve the aforementioned performance, the controller consists of a parallel structure comprising two controllers: a feedback controller, which renders the system strictly positive real, and nonlinear controller, which renders the object asymptotic to the target. First, we confirm cooperative transportation using 8 and 10 robots for two shapes via numerical simulation. Subsequently, the cooperative transportation of a rectangle payload (with a weight of approximately 3 kg and maximum length of 1.6 m) is demonstrated using a robot team consisting of three types of robots, even under robot failure and center of mass fluctuation.

The nature of explanations provided by an explainable AI algorithm has been a topic of interest in the explainable AI and human-computer interaction community. In this paper, we investigate the effects of natural language explanations' specificity on passengers in autonomous driving. We extended an existing data-driven tree-based explainer algorithm by adding a rule-based option for explanation generation. We generated auditory natural language explanations with different levels of specificity (abstract and specific) and tested these explanations in a within-subject user study (N=39) using an immersive physical driving simulation setup. Our results showed that both abstract and specific explanations had similar positive effects on passengers' perceived safety and the feeling of anxiety. However, the specific explanations influenced the desire of passengers to takeover driving control from the autonomous vehicle (AV), while the abstract explanations did not. We conclude that natural language auditory explanations are useful for passengers in autonomous driving, and their specificity levels could influence how much in-vehicle participants would wish to be in control of the driving activity.

Optimizer is an essential component for the success of deep learning, which guides the neural network to update the parameters according to the loss on the training set. SGD and Adam are two classical and effective optimizers on which researchers have proposed many variants, such as SGDM and RAdam. In this paper, we innovatively combine the backward-looking and forward-looking aspects of the optimizer algorithm and propose a novel \textsc{Admeta} (\textbf{A} \textbf{D}ouble exponential \textbf{M}oving averag\textbf{E} \textbf{T}o \textbf{A}daptive and non-adaptive momentum) optimizer framework. For backward-looking part, we propose a DEMA variant scheme, which is motivated by a metric in the stock market, to replace the common exponential moving average scheme. While in the forward-looking part, we present a dynamic lookahead strategy which asymptotically approaches a set value, maintaining its speed at early stage and high convergence performance at final stage. Based on this idea, we provide two optimizer implementations, \textsc{AdmetaR} and \textsc{AdmetaS}, the former based on RAdam and the latter based on SGDM. Through extensive experiments on diverse tasks, we find that the proposed \textsc{Admeta} optimizer outperforms our base optimizers and shows advantages over recently proposed competitive optimizers. We also provide theoretical proof of these two algorithms, which verifies the convergence of our proposed \textsc{Admeta}.

In modern scientific applications, data are often observed in the form of multiple matrices or tensors that pertain to different subjects from a certain population. For instance, longitudinal gene expression data consist of a matrix of gene expression levels across time for each subject (Liu et al., 2017); MRI imaging data contain one order-3 tensor image for each patient (Zhou et al., 2013); multilayer network can be represented by an order-3 tensor, where each layer (i.e., a matrix) represents one network (Jing et al., 2021); m-uniform hypergraph is typically viewed as an order-m tensor, whose entries denote all hyper-edges (Zhen & Wang, 2022); atomicresolution 4D scanning transmission electron microscopy data can be expressed as an order-3 tensor with two models denoting scan location and the other denoting the convergent beam electron diffraction pattern (Zhang et al., 2020). Combining information from all subjects results in a high-order tensor with subject independence along one mode and some covariance structure along the other modes that represent the relationship among the measured covariates. Principal Component Analysis (PCA) is a widely accepted method for analyzing data consisting of vectors associated with individual subjects. Its primary objective is to identify a lower-dimensional subspace within the feature domain that captures the majority of data variance (Pearson, 1901).

Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the user's intent. Existing approaches to semi-supervised clustering require a significant amount of feedback from an expert to improve the clusters. In this paper, we ask whether a large language model can amplify an expert's guidance to enable query-efficient, few-shot semi-supervised text clustering. We show that LLMs are surprisingly effective at improving clustering. We explore three stages where LLMs can be incorporated into clustering: before clustering (improving input features), during clustering (by providing constraints to the clusterer), and after clustering (using LLMs post-correction). We find incorporating LLMs in the first two stages can routinely provide significant improvements in cluster quality, and that LLMs enable a user to make trade-offs between cost and accuracy to produce desired clusters. We release our code and LLM prompts for the public to use.

Generating learning-friendly representations for points in space is a fundamental and long-standing problem in ML. Recently, multi-scale encoding schemes (such as Space2Vec and NeRF) were proposed to directly encode any point in 2D/3D Euclidean space as a high-dimensional vector, and has been successfully applied to various geospatial prediction and generative tasks. However, all current 2D and 3D location encoders are designed to model point distances in Euclidean space. So when applied to large-scale real-world GPS coordinate datasets, which require distance metric learning on the spherical surface, both types of models can fail due to the map projection distortion problem (2D) and the spherical-to-Euclidean distance approximation error (3D). To solve these problems, we propose a multi-scale location encoder called Sphere2Vec which can preserve spherical distances when encoding point coordinates on a spherical surface. We developed a unified view of distance-reserving encoding on spheres based on the DFS. We also provide theoretical proof that the Sphere2Vec preserves the spherical surface distance between any two points, while existing encoding schemes do not. Experiments on 20 synthetic datasets show that Sphere2Vec can outperform all baseline models on all these datasets with up to 30.8% error rate reduction. We then apply Sphere2Vec to three geo-aware image classification tasks - fine-grained species recognition, Flickr image recognition, and remote sensing image classification. Results on 7 real-world datasets show the superiority of Sphere2Vec over multiple location encoders on all three tasks. Further analysis shows that Sphere2Vec outperforms other location encoder models, especially in the polar regions and data-sparse areas because of its nature for spherical surface distance preservation. Code and data are available at https://gengchenmai.github.io/sphere2vec-website/.