在具有连续以对象的状态，连续的动作，长距离和稀疏反馈的机器人环境中，决策是具有挑战性的。诸如任务和运动计划（TAMP）之类的层次结构方法通过将决策分解为两个或更多级别的抽象来解决这些挑战。在给出演示和符号谓词的环境中，先前的工作已经显示了如何通过手动设计的参数化策略来学习符号操作员和神经采样器。我们的主要贡献是一种与操作员和采样器结合使用的参数化策略的方法。这些组件被包装到模块化神经符号技能中，并与搜索 - 然后样本tamp一起测序以解决新任务。在四个机器人域的实验中，我们表明我们的方法 - 具有神经符号技能的双重计划 - 可以解决具有不同初始状态，目标和对象不同的各种任务，表现优于六个基线和消融。视频：https：//youtu.be/pbfzp8rpugg代码：https：//tinyurl.com/skill-learning

在机器人域中，学习和计划因连续的状态空间，连续的动作空间和较长的任务范围而变得复杂。在这项工作中，我们通过神经符号关系过渡模型（NSRTS）解决了这些挑战，这是一种具有数据效率学习的新型模型，与强大的机器人计划方法兼容，并且可以推广到对象上。NSRT具有符号和神经成分，实现了双重计划方案，其中外循环中的符号AI规划指导内部循环中的神经模型的连续计划。四个机器人计划域中的实验表明，仅在数十或数百个培训情节之后就可以学习NSRT，然后用于快速规划的新任务，这些任务需要高达60个动作，并且涉及比培训期间看到的更多物体。视频：https：//tinyurl.com/chitnis-nsrts

在家庭中运行的机器人可以观察到多个物体在几天或几周内移动时。这些物体可以被居民移动，但不是完全随机的。稍后可以要求机器人检索对象，并需要一个基于对象的内存才能知道如何找到它们。语义大满贯中现有的工作并不试图捕获对象运动的动态。在本文中，我们将用于数据缔合过滤的经典技术与现代化的神经网络相结合，以构建基于对象的内存系统，这些系统在高维观察和假设上运行。我们对标记的观察轨迹进行端到端学习，以学习过渡和观察模型。我们证明了系统在模拟环境和真实图像中动态变化对象的记忆方面的有效性，并证明了对经典结构化方法以及非结构化神经方法的改进。在项目网站上获得的其他信息：https：//yilundu.github.io/obm/。

Recent advances in deep learning have enabled us to address the curse of dimensionality (COD) by solving problems in higher dimensions. A subset of such approaches of addressing the COD has led us to solving high-dimensional PDEs. This has resulted in opening doors to solving a variety of real-world problems ranging from mathematical finance to stochastic control for industrial applications. Although feasible, these deep learning methods are still constrained by training time and memory. Tackling these shortcomings, Tensor Neural Networks (TNN) demonstrate that they can provide significant parameter savings while attaining the same accuracy as compared to the classical Dense Neural Network (DNN). In addition, we also show how TNN can be trained faster than DNN for the same accuracy. Besides TNN, we also introduce Tensor Network Initializer (TNN Init), a weight initialization scheme that leads to faster convergence with smaller variance for an equivalent parameter count as compared to a DNN. We benchmark TNN and TNN Init by applying them to solve the parabolic PDE associated with the Heston model, which is widely used in financial pricing theory.

In the future, service robots are expected to be able to operate autonomously for long periods of time without human intervention. Many work striving for this goal have been emerging with the development of robotics, both hardware and software. Today we believe that an important underpinning of long-term robot autonomy is the ability of robots to learn on site and on-the-fly, especially when they are deployed in changing environments or need to traverse different environments. In this paper, we examine the problem of long-term autonomy from the perspective of robot learning, especially in an online way, and discuss in tandem its premise "data" and the subsequent "deployment".

Factorization machines (FMs) are a powerful tool for regression and classification in the context of sparse observations, that has been successfully applied to collaborative filtering, especially when side information over users or items is available. Bayesian formulations of FMs have been proposed to provide confidence intervals over the predictions made by the model, however they usually involve Markov-chain Monte Carlo methods that require many samples to provide accurate predictions, resulting in slow training in the context of large-scale data. In this paper, we propose a variational formulation of factorization machines that allows us to derive a simple objective that can be easily optimized using standard mini-batch stochastic gradient descent, making it amenable to large-scale data. Our algorithm learns an approximate posterior distribution over the user and item parameters, which leads to confidence intervals over the predictions. We show, using several datasets, that it has comparable or better performance than existing methods in terms of prediction accuracy, and provide some applications in active learning strategies, e.g., preference elicitation techniques.

By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can solve specific downstream tasks either zero-shot or with small task-specific datasets to a high level of performance. While this capability has been demonstrated in other fields such as computer vision, natural language processing or speech recognition, it remains to be shown in robotics, where the generalization capabilities of the models are particularly critical due to the difficulty of collecting real-world robotic data. We argue that one of the keys to the success of such general robotic models lies with open-ended task-agnostic training, combined with high-capacity architectures that can absorb all of the diverse, robotic data. In this paper, we present a model class, dubbed Robotics Transformer, that exhibits promising scalable model properties. We verify our conclusions in a study of different model classes and their ability to generalize as a function of the data size, model size, and data diversity based on a large-scale data collection on real robots performing real-world tasks. The project's website and videos can be found at robotics-transformer.github.io

This case study investigates the extent to which a language model (GPT-2) is able to capture native speakers' intuitions about implicit causality in a sentence completion task. We first reproduce earlier results (showing lower surprisal values for pronouns that are congruent with either the subject or object, depending on which one corresponds to the implicit causality bias of the verb), and then examine the effects of gender and verb frequency on model performance. Our second study examines the reasoning ability of GPT-2: is the model able to produce more sensible motivations for why the subject VERBed the object if the verbs have stronger causality biases? We also developed a methodology to avoid human raters being biased by obscenities and disfluencies generated by the model.

Semi-supervised anomaly detection is a common problem, as often the datasets containing anomalies are partially labeled. We propose a canonical framework: Semi-supervised Pseudo-labeler Anomaly Detection with Ensembling (SPADE) that isn't limited by the assumption that labeled and unlabeled data come from the same distribution. Indeed, the assumption is often violated in many applications - for example, the labeled data may contain only anomalies unlike unlabeled data, or unlabeled data may contain different types of anomalies, or labeled data may contain only 'easy-to-label' samples. SPADE utilizes an ensemble of one class classifiers as the pseudo-labeler to improve the robustness of pseudo-labeling with distribution mismatch. Partial matching is proposed to automatically select the critical hyper-parameters for pseudo-labeling without validation data, which is crucial with limited labeled data. SPADE shows state-of-the-art semi-supervised anomaly detection performance across a wide range of scenarios with distribution mismatch in both tabular and image domains. In some common real-world settings such as model facing new types of unlabeled anomalies, SPADE outperforms the state-of-the-art alternatives by 5% AUC in average.

We propose a method for in-hand 3D scanning of an unknown object from a sequence of color images. We cast the problem as reconstructing the object surface from un-posed multi-view images and rely on a neural implicit surface representation that captures both the geometry and the appearance of the object. By contrast with most NeRF-based methods, we do not assume that the camera-object relative poses are known and instead simultaneously optimize both the object shape and the pose trajectory. As global optimization over all the shape and pose parameters is prone to fail without coarse-level initialization of the poses, we propose an incremental approach which starts by splitting the sequence into carefully selected overlapping segments within which the optimization is likely to succeed. We incrementally reconstruct the object shape and track the object poses independently within each segment, and later merge all the segments by aligning poses estimated at the overlapping frames. Finally, we perform a global optimization over all the aligned segments to achieve full reconstruction. We experimentally show that the proposed method is able to reconstruct the shape and color of both textured and challenging texture-less objects, outperforms classical methods that rely only on appearance features, and its performance is close to recent methods that assume known camera poses.